© 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-2-2B
    7. Residual Stream - 16k
    9. 17-GEMMASCOPE-RES-16K
    11. 893
    Prev
    Next
    INDEX
    Explanations

    concepts related to evasion or escape, particularly in a legal or disciplinary context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    featureID
    -0.77
    ThroughAttribute
    -0.76
    ValueStyle
    -0.55
    aarrggbb
    -0.54
    </tfoot>
    -0.52
     lumens
    -0.52
    IsPostBack
    -0.51
    moveToFirst
    -0.50
    SOUNDBITE
    -0.50
    ISupport
    -0.48
    POSITIVE LOGITS
     escape
    1.11
     escaped
    1.09
     escapes
    0.99
     unsc
    0.97
     spared
    0.93
     escaping
    0.91
     dodged
    0.90
    escape
    0.88
     lucky
    0.84
     Avoiding
    0.83
    Activations Density 0.224%

    No Known Activations