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. 8-GEMMASCOPE-RES-16K
    6. 8885
    Prev
    Next
    INDEX
    Explanations

    quantitative data relating to biological measurements and comparisons

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     חיצוניים
    -1.17
    Hauptartikel
    -1.05
     дописавши
    -1.05
    lgari
    -0.94
    NameInMap
    -0.92
     ***!
    -0.89
     AssemblyCulture
    -0.87
    Tembelea
    -0.86
     صوتيه
    -0.83
    -------
    -0.83
    POSITIVE LOGITS
    Craw
    0.60
    1
    0.57
    lessly
    0.55
    2
    0.53
    3
    0.53
     /\.
    0.52
    Rich
    0.52
     Rich
    0.52
    neu
    0.51
     Petty
    0.51
    Activations Density 0.267%

    No Known Activations