© 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. 40-GEMMASCOPE-RES-16K
    6. 6228
    Prev
    Next
    INDEX
    Explanations

    mentions of government and economic entities or concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 40-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_40/width_16k/average_l0_125
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.40.hook_resid_post
    Hook Layer
    40
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    RTGC
    -0.41
    StoreMessageInfo
    -0.40
    Warmly
    -0.40
    RTSN
    -0.40
    sendRedirect
    -0.39
    
    -0.38
    CppCodeGen
    -0.37
    fromnode
    -0.37
     دریا
    -0.35
     durer
    -0.35
    POSITIVE LOGITS
     Center
    0.53
    Center
    0.50
    Demos
    0.49
     Pew
    0.46
    verwijspagina
    0.45
     think
    0.44
     חיצוניים
    0.44
    ecap
    0.44
     rowspan
    0.43
    enderror
    0.43
    Activations Density 0.462%

    No Known Activations