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-IT
    4. Residual Stream - 131k
    5. 9-GEMMASCOPE-RES-131K
    6. 24625
    Prev
    Next
    INDEX
    Explanations

    technical terms and personal expressions related to programming and self-reference

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

    pronouns and conjunctions

    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
    httphttps
    -0.51
    moc
    -0.43
     bocca
    -0.43
     perhaps
    -0.43
    unfinished
    -0.42
    block
    -0.42
    perhaps
    -0.41
     Grandes
    -0.41
     PJ
    -0.40
     Kearns
    -0.40
    POSITIVE LOGITS
    ว่า
    1.93
     ว่า
    1.50
     rằng
    0.91
    ]")]
    0.76
     hogy
    0.73
     πως
    0.71
    }")]
    0.69
    กว่า
    0.67
    "?>
    0.66
    }));
    
    0.63
    Activations Density 0.002%

    No Known Activations