© 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. 25-GEMMASCOPE-RES-16K
    6. 516
    Prev
    Next
    INDEX
    Explanations

    expressions indicating visual representation or appearance

    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
    tvguidetime
    -0.69
     Types
    -0.63
    IsContent
    -0.63
    RuleContext
    -0.61
    帖最后由
    -0.61
     Kinds
    -0.61
     EconPapers
    -0.58
    Type
    -0.57
    SequentialGroup
    -0.57
    loài
    -0.56
    POSITIVE LOGITS
     li
    0.61
     liked
    0.60
     liking
    0.54
     lenker
    0.53
     lie
    0.53
    تقاوى
    0.53
    Gambas
    0.53
    AllowAnonymous
    0.52
     slike
    0.51
    KURZBESCHREIBUNG
    0.50
    Activations Density 0.124%

    No Known Activations