© 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-2-2B
    7. Residual Stream - 16k
    9. 22-GEMMASCOPE-RES-16K
    11. 11210
    Prev
    Next
    INDEX
    Explanations

    references to "char" in various contexts, likely related to character types or charred items

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

    "Char" followed by specific characters

    np_acts-logits-general · gemini-2.0-flash

    words starting with char

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    CloseOperation
    -0.78
    Enllaces
    -0.72
     AssemblyCulture
    -0.70
     égard
    -0.67
    ///<
    -0.66
     OnInit
    -0.66
    erover
    -0.65
    +:+
    -0.64
     petto
    -0.63
     QtCore
    -0.62
    POSITIVE LOGITS
    Char
    0.69
     Char
    0.63
     char
    0.51
    achter
    0.51
     CHAR
    0.50
    char
    0.50
    CHAR
    0.50
     poto
    0.49
     Universitaria
    0.48
    itable
    0.45
    Activations Density 0.113%

    No Known Activations