© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 9-GEMMASCOPE-RES-131K
    6. 17447
    Prev
    Next
    INDEX
    Explanations

    instances of the word "nobody."

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

    nobody followed by a verb

    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
     GenerationType
    -0.59
    SourceChecksum
    -0.47
     ͡°)
    -0.47
    batore
    -0.45
    indrical
    -0.44
     Stearns
    -0.43
     Act
    -0.43
    uParam
    -0.42
    ffindor
    -0.42
    ukung
    -0.41
    POSITIVE LOGITS
     nobody
    2.20
    Nobody
    2.13
     Nobody
    2.11
    nobody
    1.96
     nadie
    1.50
     Niemand
    1.41
    Nadie
    1.40
     niemand
    1.36
     Nadie
    1.35
     ninguém
    1.31
    Activations Density 0.003%

    No Known Activations