© 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. 25-GEMMASCOPE-RES-16K
    6. 244
    Prev
    Next
    INDEX
    Explanations

    quantifiable measures and comparisons related to outcomes and efficacy

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     autorytatywna
    -0.75
    Hochspringen
    -0.71
     Roskov
    -0.69
    More
    -0.67
     дописавши
    -0.63
    RectangleBorder
    -0.63
    GOTREF
    -0.62
    Più
    -0.61
     CreateTagHelper
    -0.58
    ToBounds
    -0.58
    POSITIVE LOGITS
     lower
    0.88
     higher
    0.81
    lower
    0.67
     louer
    0.63
    出版年
    0.60
     resourceCulture
    0.59
     lager
    0.58
     larger
    0.57
     father
    0.56
     systematically
    0.56
    Activations Density 0.464%

    No Known Activations