© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 15-GEMMASCOPE-RES-16K
    6. 8303
    Prev
    Next
    INDEX
    Explanations

    references to strings and string manipulation in programming contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    adaptiveStyles
    -0.93
     Nema
    -0.85
     Toul
    -0.84
    solete
    -0.83
    ึกษา
    -0.82
     scaricare
    -0.81
     gdyby
    -0.77
    cinations
    -0.76
    UrlResolution
    -0.76
    PhysRev
    -0.74
    POSITIVE LOGITS
    ling
    1.00
    ly
    0.98
    er
    0.85
    king
    0.77
    y
    0.75
    string
    0.75
     rootReducer
    0.73
    ster
    0.73
     Pais
    0.73
    rentina
    0.70
    Activations Density 0.076%

    No Known Activations