Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 11-GEMMASCOPE-RES-16K
    6. 13681
    Prev
    Next
    INDEX
    Explanations

    mentions of the Bay area

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     againſt
    -0.92
     Lassen
    -0.86
    Zunanje
    -0.84
     Perſ
    -0.81
     Majefty
    -0.80
    RenderAtEndOf
    -0.79
    UrlResolution
    -0.79
     Conſ
    -0.79
     ESE
    -0.78
     Houſe
    -0.78
    POSITIVE LOGITS
     Kett
    0.82
     Bay
    0.82
     Qi
    0.77
    ophor
    0.75
     BAY
    0.74
     Carol
    0.74
     Ott
    0.73
    Gott
    0.73
     Mont
    0.72
     Biss
    0.72
    Activations Density 0.285%

    No Known Activations