© 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. 8-GEMMASCOPE-RES-16K
    6. 6862
    Prev
    Next
    INDEX
    Explanations

    actions or terms related to removing or altering states, particularly "strip" and "reset."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Sphere
    -0.87
     MatDialog
    -0.85
     Colman
    -0.82
     odkazy
    -0.82
    Crossref
    -0.81
     SVC
    -0.81
    Törté
    -0.78
     CURIAM
    -0.77
     Martinique
    -0.76
     betweenstory
    -0.76
    POSITIVE LOGITS
    strip
    1.04
     strip
    0.96
     Strip
    0.86
     STRIP
    0.84
    STRIP
    0.84
    Strip
    0.83
     stripped
    0.77
     stripping
    0.76
    reset
    0.73
     strips
    0.69
    Activations Density 0.115%

    No Known Activations