© 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. 27-GEMMASCOPE-RES-16K
    6. 9429
    Prev
    Next
    INDEX
    Explanations

    references to local educational initiatives and partnerships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 27-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_27/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.27.hook_resid_post
    Hook Layer
    27
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    /**
    -0.59
    rungsseite
    -0.59
    posedge
    -0.52
     Yunnan
    -0.51
    
    -0.50
    AccessorTable
    -0.49
    WireFormatLite
    -0.47
    Seattle
    -0.47
    MigrationBuilder
    -0.47
     jspb
    -0.45
    POSITIVE LOGITS
     NJ
    1.15
    NJ
    1.05
     Jersey
    0.99
     Newark
    0.97
     nj
    0.96
     Rutgers
    0.90
    Jersey
    0.87
     JERSEY
    0.84
    Newark
    0.84
    nj
    0.80
    Activations Density 0.534%

    No Known Activations