© 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. 18-GEMMASCOPE-RES-16K
    11. 1701
    Prev
    Next
    INDEX
    Explanations

    patterns related to structured data or code, possibly indicating variable or object identifiers

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

    "s" followed by specific characters

    np_acts-logits-general · gemini-2.0-flash

    s followed by slash or substitution

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    __*/
    -0.83
    IntoConstraints
    -0.81
    ])):
    -0.78
     Paglinawan
    -0.74
     @"/
    -0.72
    oluble
    -0.69
     برانيه
    -0.69
    tanleria
    -0.68
    __))
    -0.68
    '])->
    -0.66
    POSITIVE LOGITS
     S
    1.01
     getS
    0.91
    getS
    0.87
     s
    0.82
    S
    0.76
     SPS
    0.67
    SSS
    0.64
     scones
    0.64
     dinosaurios
    0.61
     Sars
    0.61
    Activations Density 0.340%

    No Known Activations