© 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. 12-GEMMASCOPE-RES-16K
    11. 9388
    Prev
    Next
    INDEX
    Explanations

    references to various forms of attack or aggression

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_12/width_16k/average_l0_130
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    sidemargin
    -0.54
    躇
    -0.49
    rungsseite
    -0.49
     uLocal
    -0.47
     Picchu
    -0.47
     zelve
    -0.46
     quiser
    -0.44
     ſein
    -0.42
     dovrebbero
    -0.42
     indígen
    -0.42
    POSITIVE LOGITS
     attack
    1.72
    attack
    1.56
     Attack
    1.48
     attacks
    1.39
     ATTACK
    1.37
    Attack
    1.36
    ATTACK
    1.27
     attacking
    1.26
     attacked
    1.23
    Attacks
    1.19
    Activations Density 0.192%

    No Known Activations