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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 5244
    Prev
    Next
    INDEX
    Explanations

    references to injury and damage

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

    pertaining to physical harm or damage

    np_acts-logits-general · gemini-2.0-flash

    damage and injury

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Autorizaciones
    -0.59
    OGND
    -0.56
    ंदीखरीदारी
    -0.53
    Rhestr
    -0.51
    PreExecute
    -0.50
    principalTable
    -0.50
    SBATCH
    -0.49
    yargs
    -0.48
     CreateTagHelper
    -0.47
     StringTokenizer
    -0.47
    POSITIVE LOGITS
    Injury
    1.09
     Damage
    1.09
     Injury
    1.08
     injury
    1.08
    Damage
    1.07
     damage
    1.03
    damage
    1.03
     injuries
    1.02
    Injuries
    0.99
    injury
    0.99
    Activations Density 0.336%

    No Known Activations