Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 23-GEMMASCOPE-RES-16K
    6. 11964
    Prev
    Next
    INDEX
    Explanations

    terms related to defense mechanisms and protective measures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ⓧ
    -0.71
    évaluateur
    -0.62
    ArgsConstructor
    -0.56
     GeoNames
    -0.55
     урна
    -0.54
    moveToFirst
    -0.51
    SourceChecksum
    -0.50
     parseFrom
    -0.50
    ]")]
    -0.49
    mények
    -0.48
    POSITIVE LOGITS
     protection
    3.17
     protect
    2.78
     Protection
    2.73
     protecting
    2.73
    protection
    2.71
    Protection
    2.59
     protects
    2.56
     protective
    2.51
     Protect
    2.48
     PROTECTION
    2.46
    Activations Density 0.674%

    No Known Activations