© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 4340
    Prev
    Next
    INDEX
    Explanations

    references to various forms of damage or harm

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    references to causing harm or damage.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi

    mentions of harm or destruction being caused or assessed, both physical and figurative, often specifying what is damaged and by whom or what

    oai_token-act-pair · gpt-5Triggered by @jyhe0408

    the word "damage" when it appears as a noun referring to harm or injury that can be caused or occur.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    OGND
    -0.57
     libremente
    -0.55
     Мексичка
    -0.55
    Jeografia
    -0.54
    BeforeClass
    -0.52
    SequentialGroup
    -0.52
    ➊
    -0.52
    rolid
    -0.50
     getGroup
    -0.50
     esimer
    -0.49
    POSITIVE LOGITS
     Damage
    1.30
     damage
    1.26
    damage
    1.24
    Damage
    1.23
     DAMAGE
    1.17
     Damaged
    1.02
     damaged
    1.01
    DAMAGE
    1.00
    damaged
    1.00
     Damages
    0.96
    Activations Density 0.090%

    No Known Activations