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-2-9B-IT
    4. Residual Stream - 131k
    5. 9-GEMMASCOPE-RES-131K
    6. 7278
    Prev
    Next
    INDEX
    Explanations

    mentions of the name "Richard."

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

    Richard followed by surname

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    cotch
    -0.58
    Gue
    -0.54
     mue
    -0.52
    ypsies
    -0.51
    couts
    -0.50
     ​​
    -0.50
    cue
    -0.50
    OPTS
    -0.50
    obey
    -0.50
    eco
    -0.50
    POSITIVE LOGITS
     Richard
    1.80
    Richard
    1.67
     RICHARD
    1.43
     richard
    1.39
    richard
    1.33
    RICHARD
    1.28
     Richards
    1.17
    Richards
    1.01
     Ricard
    0.81
     Richardson
    0.77
    Activations Density 0.004%

    No Known Activations