© 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. 978
    Prev
    Next
    INDEX
    Explanations

    intensifiers related to totality or completeness

    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
     slightly
    -0.82
     somewhat
    -0.79
     partially
    -0.75
    slightly
    -0.74
     partly
    -0.73
    AddHtmlAttribute
    -0.73
     altogether
    -0.73
     Slightly
    -0.72
     very
    -0.70
    somewhat
    -0.68
    POSITIVE LOGITS
    летия
    0.70
     utafitiHapana
    0.70
    IGraphics
    0.65
    存于互联网档案馆
    0.56
    tly
    0.56
    astéroïdes
    0.55
     immers
    0.55
     opposite
    0.54
     immerse
    0.53
    pendente
    0.53
    Activations Density 0.217%

    No Known Activations