© 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. 7-GEMMASCOPE-RES-16K
    6. 16003
    Prev
    Next
    INDEX
    Explanations

    code snippets and structures related to programming and data parsing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_7/width_16k/average_l0_92
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    DockStyle
    -0.97
    MessageTagHelper
    -0.86
     يتيمه
    -0.84
    ReusableCell
    -0.83
    الحياه
    -0.83
    évaluateur
    -0.82
    protoimpl
    -0.81
    +#+#
    -0.80
    ロウィン
    -0.79
    [@BOS@]
    -0.78
    POSITIVE LOGITS
     various
    0.35
    .
    0.33
     commercial
    0.33
     itself
    0.32
     industry
    0.31
     esencial
    0.29
     television
    0.28
    -
    0.26
     primarily
    0.25
     lots
    0.25
    Activations Density 2.187%

    No Known Activations