© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 0-GEMMASCOPE-RES-16K
    11. 7414
    Prev
    Next
    INDEX
    Explanations

    mentions of various types of "stations"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_0/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     itſelf
    -1.18
     ſche
    -1.13
     faſt
    -1.09
     indígen
    -1.09
     ſind
    -1.09
     houſe
    -1.02
     Monfieur
    -1.02
     againſt
    -1.02
     leſs
    -1.02
     increí
    -1.01
    POSITIVE LOGITS
     station
    0.87
    ;
    0.85
    .
    0.83
    ,
    0.81
    -
    0.72
     and
    0.69
     I
    0.68
    ↵↵
    0.67
     of
    0.65
     
    0.65
    Activations Density 0.432%

    No Known Activations