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. 31-GEMMASCOPE-RES-16K
    6. 2952
    Prev
    Next
    INDEX
    Explanations

    terms related to family-owned businesses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    descriptions of established family-owned businesses and their histories.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     gug
    -0.37
     lej
    -0.37
     interstitial
    -0.35
     ensi
    -0.35
     UU
    -0.33
    onSearch
    -0.33
    ujin
    -0.33
    ">//
    -0.33
    рно
    -0.32
    abcdef
    -0.32
    POSITIVE LOGITS
     family
    1.56
    family
    1.40
     familiale
    1.37
     FAMILY
    1.29
    Family
    1.25
     familial
    1.23
     Family
    1.21
    家族
    1.19
     rodzin
    1.16
     família
    1.16
    Activations Density 0.286%

    No Known Activations