© 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. 25-GEMMASCOPE-RES-16K
    11. 6893
    Prev
    Next
    INDEX
    Explanations

    code structure, such as function calls and error messages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     виправивши
    -0.52
    emptyList
    -0.51
    nonatomic
    -0.49
    Carriera
    -0.49
    senza
    -0.48
    municipi
    -0.48
    SerializedSize
    -0.47
    =/
    -0.47
     Familienname
    -0.47
    incontro
    -0.47
    POSITIVE LOGITS
    fflush
    0.84
    exit
    0.73
     calendriers
    0.66
     exit
    0.64
     getchar
    0.62
    sys
    0.62
    Sleep
    0.58
    sleep
    0.57
    SequentialGroup
    0.56
     //$
    0.56
    Activations Density 0.078%

    No Known Activations