© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 3-GEMMASCOPE-RES-16K
    6. 5900
    Prev
    Next
    INDEX
    Explanations

    terms related to injury and harm

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ngrx
    -0.69
    AndEndTag
    -0.58
     непре
    -0.54
    startActivity
    -0.54
    httphttps
    -0.54
    migrationBuilder
    -0.53
    DotNetBar
    -0.53
    VersionUID
    -0.52
    勿
    -0.52
    writeFieldEnd
    -0.52
    POSITIVE LOGITS
     injured
    1.84
     wounded
    1.73
     Injured
    1.64
     damaged
    1.63
     Damaged
    1.60
    injured
    1.58
    damaged
    1.54
    Damaged
    1.44
     diseased
    1.38
    Injured
    1.34
    Activations Density 0.293%

    No Known Activations