© 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. 3-GEMMASCOPE-RES-16K
    11. 5807
    Prev
    Next
    INDEX
    Explanations

    numeric representations or counts, particularly focusing on the occurrence and significance of the number "one."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     EconPapers
    -0.93
     للاسماء
    -0.90
    LookAnd
    -0.81
    RenderAtEndOf
    -0.81
     estekak
    -0.79
     AssemblyCulture
    -0.75
     propOrder
    -0.73
     informée
    -0.71
     iprot
    -0.70
     Италијани
    -0.69
    POSITIVE LOGITS
    gogo
    0.35
    OneToOne
    0.35
    /
    0.33
     in
    0.32
     UU
    0.31
     text
    0.30
    c
    0.30
      
    0.29
    PP
    0.29
    ManyToMany
    0.29
    Activations Density 0.363%

    No Known Activations