© 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-2-9B
    4. Residual Stream - 16k
    5. 33-GEMMASCOPE-RES-16K
    6. 8282
    Prev
    Next
    INDEX
    Explanations

    keywords related to legal and policy processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     esternos
    -0.85
     estadounid
    -0.85
    LookAnd
    -0.84
     AssemblyCulture
    -0.83
     好文分享
    -0.79
    <unused51>
    -0.77
    <unused43>
    -0.77
    ChildScrollView
    -0.77
    <unused42>
    -0.77
    <unused1>
    -0.77
    POSITIVE LOGITS
    ize
    0.30
    en
    0.22
    ise
    0.22
     dab
    0.19
     fat
    0.19
     sobie
    0.19
    itize
    0.18
    ulate
    0.18
    reg
    0.18
    clude
    0.18
    Activations Density 0.535%

    No Known Activations