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. 3-GEMMASCOPE-RES-16K
    6. 6101
    Prev
    Next
    INDEX
    Explanations

    file extensions and related keywords

    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
    GOTREF
    -1.05
    findpost
    -0.97
    RenderAtEndOf
    -0.91
    etheless
    -0.82
    errHandler
    -0.82
    olisme
    -0.81
    ✨:
    -0.80
    endphp
    -0.80
    matchCondition
    -0.76
     useRouter
    -0.76
    POSITIVE LOGITS
    ext
    3.02
    Ext
    2.99
     Ext
    2.97
     ext
    2.92
    EXT
    2.46
     EXT
    2.33
    xt
    1.71
     exten
    1.48
     extender
    1.48
     xt
    1.40
    Activations Density 0.067%

    No Known Activations