Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 17-GEMMASCOPE-RES-16K
    6. 10850
    Prev
    Next
    INDEX
    Explanations

    elements of code that define data structures and their manipulations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Reſ
    -0.73
     Monfieur
    -0.70
    roek
    -0.69
     Diſ
    -0.67
     iſt
    -0.67
    phalt
    -0.66
    /**
    -0.64
     faſt
    -0.64
     ſche
    -0.63
    ReusableCell
    -0.63
    POSITIVE LOGITS
    return
    0.52
     ""],
    0.51
    SuccessListener
    0.50
    abestanden
    0.50
    memoized
    0.46
    IVEREF
    0.46
     Réponses
    0.43
    }}}{\
    0.43
     najleps
    0.42
    Personensuche
    0.41
    Activations Density 0.037%

    No Known Activations