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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 14178
    Prev
    Next
    INDEX
    Explanations

    terms related to astronomical phenomena and structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     stanovnika
    -0.48
    EReference
    -0.47
    enterOuterAlt
    -0.47
     menar
    -0.47
    openzeppelin
    -0.46
    MarshalTo
    -0.46
    ը
    -0.46
    msgTypes
    -0.46
    Географи
    -0.46
    ...”
    -0.45
    POSITIVE LOGITS
     فريبيس
    0.79
    省市镇
    0.67
     يتيمه
    0.65
     المعيارى
    0.60
     Dorm
    0.59
    dymyr
    0.59
     snippetHide
    0.58
    󠁬
    0.58
    bewerken
    0.56
    <tbody>
    0.56
    Activations Density 0.374%

    No Known Activations