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. 12-GEMMASCOPE-RES-16K
    6. 14875
    Prev
    Next
    INDEX
    Explanations

    hyperlinks or references in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    expandindo
    -0.97
    :✨
    -0.93
    TypedDataSet
    -0.90
    bewerken
    -0.89
    rungsseite
    -0.86
     препратки
    -0.85
    Tikang
    -0.83
     Yad
    -0.81
     oprot
    -0.80
     Lando
    -0.79
    POSITIVE LOGITS
     href
    1.45
     the
    0.80
     https
    0.73
     http
    0.65
    Href
    0.64
    https
    0.61
     a
    0.58
    http
    0.58
     to
    0.56
     cref
    0.56
    Activations Density 0.038%

    No Known Activations