© 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. 12908
    Prev
    Next
    INDEX
    Explanations

    commands related to identity and credential management in a coding or command context

    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
    De
    -0.48
    Re
    -0.47
    Sh
    -0.47
    Ge
    -0.47
    En
    -0.47
    Se
    -0.47
    Me
    -0.46
    Na
    -0.46
    Ch
    -0.46
    Che
    -0.46
    POSITIVE LOGITS
    rate
    0.25
    size
    0.24
    list
    0.23
    range
    0.23
    time
    0.23
    data
    0.22
    line
    0.22
    providedIn
    0.22
    name
    0.22
    date
    0.22
    Activations Density 32.850%

    No Known Activations