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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 15602
    Prev
    Next
    INDEX
    Explanations

    technical terms and structures related to programming and data handling

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 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
     незавершена
    -0.60
    TagMode
    -0.58
     raiſ
    -0.57
    outheast
    -0.54
    jsonwebtoken
    -0.53
    GIVEREF
    -0.53
    mopolitan
    -0.52
     виправивши
    -0.52
     ſeveral
    -0.51
    InInspector
    -0.50
    POSITIVE LOGITS
    アリング
    0.36
    ReusableCell
    0.35
    onAttach
    0.33
     '{@
    0.31
     bordada
    0.30
     året
    0.30
    ัก
    0.29
     francès
    0.29
     cuánto
    0.29
     chart
    0.29
    Activations Density 0.447%

    No Known Activations