© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 24-GEMMASCOPE-RES-16K
    6. 2723
    Prev
    Next
    INDEX
    Explanations

    contextual references to objects and their characteristics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Adjectives describing condition or appearance

    np_acts-logits-general · gemini-2.0-flash

    describing worn or altered states

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    kään
    -0.56
     getItemId
    -0.55
     ContentValues
    -0.53
    AutoScaleMode
    -0.52
    MessageOf
    -0.51
     calendriers
    -0.50
    揄
    -0.50
     coû
    -0.49
    opsida
    -0.49
    طلحات
    -0.48
    POSITIVE LOGITS
     wider
    0.73
     firm
    0.71
     detachable
    0.67
     sturdy
    0.67
     smooth
    0.65
     removable
    0.64
     thicker
    0.64
     taller
    0.63
    verwijspagina
    0.63
     larger
    0.63
    Activations Density 0.394%

    No Known Activations