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-2-9B
    4. Residual Stream - 16k
    5. 40-GEMMASCOPE-RES-16K
    6. 5933
    Prev
    Next
    INDEX
    Explanations

    structured data and return types in coding contexts

    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
    AndEndTag
    -0.69
     للاسماء
    -0.59
    ChildScrollView
    -0.53
    DBNull
    -0.51
    AnimationsModule
    -0.50
    exitRule
    -0.49
     Normdatei
    -0.48
    appé
    -0.46
     ModelRenderer
    -0.46
     newOwner
    -0.45
    POSITIVE LOGITS
    ...}
    0.57
    !}
    0.52
    $}
    0.51
     ''}
    0.51
    ;}
    
    0.50
    ?}
    0.49
     ""}
    0.47
    ()};
    0.47
    ()}
    0.46
     Meksi
    0.46
    Activations Density 2.031%

    No Known Activations