© 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. 31-GEMMASCOPE-RES-16K
    11. 507
    Prev
    Next
    INDEX
    Explanations

    references to individuals in positions of authority or leadership roles

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

    government officials and political figures identified by their titles and names.

    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
     į
    -0.35
     tø
    -0.35
     sty
    -0.35
     ‘
    -0.35
     coaching
    -0.34
     Muriel
    -0.34
     grø
    -0.34
     pagină
    -0.33
    Number
    -0.33
    <bos>
    -0.33
    POSITIVE LOGITS
     createSlice
    0.65
     AssemblyCompany
    0.63
     forState
    0.57
    Personendaten
    0.57
     ब्रेकडाउन
    0.57
    Tembelea
    0.56
     iprot
    0.56
    ьаж
    0.56
    HtmlAttribute
    0.54
    OGND
    0.54
    Activations Density 0.221%

    No Known Activations