© 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-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 106627
    Prev
    Next
    INDEX
    Explanations

    references to the name "Charlotte."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Brethren
    -0.41
    ]};
    -0.40
     sû
    -0.39
    toThrow
    -0.39
    _));
    -0.39
    routeProvider
    -0.38
    ("}\
    -0.38
    )))
    -0.37
     elif
    -0.37
     bookId
    -0.36
    POSITIVE LOGITS
     Charlotte
    1.16
    Charlotte
    1.12
    LOTTE
    1.10
    charlotte
    1.06
     charlotte
    0.88
    lottes
    0.73
    Castell
    0.64
    lotte
    0.61
     Castell
    0.59
    lotta
    0.56
    Activations Density 0.003%

    No Known Activations