© 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. 35-GEMMASCOPE-RES-16K
    6. 7910
    Prev
    Next
    INDEX
    Explanations

    terms related to verification and updates in policies or information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 35-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_35/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.35.hook_resid_post
    Hook Layer
    35
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AutoScaleMode
    -0.48
     ExecuteAsync
    -0.47
    DockStyle
    -0.47
     estekak
    -0.43
    libatkan
    -0.43
    ftagPool
    -0.42
    ViewInit
    -0.41
    SharedCtor
    -0.41
    تقاوى
    -0.40
     Taktlose
    -0.40
    POSITIVE LOGITS
     updated
    1.58
     latest
    1.43
    最新
    1.31
    最新的
    1.25
    latest
    1.23
     current
    1.22
    Latest
    1.21
     uppdater
    1.19
     updating
    1.18
     abreast
    1.18
    Activations Density 0.404%

    No Known Activations