© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 25-GEMMASCOPE-RES-16K
    11. 2289
    Prev
    Next
    INDEX
    Explanations

    references to educational strategies and student assessment tools

    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
    الإنجليزية
    -0.78
    Portail
    -0.69
     HasFactory
    -0.68
    KURZBESCHREIBUNG
    -0.67
    findpost
    -0.63
    TableHead
    -0.61
     propOrder
    -0.60
    SizeF
    -0.60
    principalTable
    -0.59
    ThroughAttribute
    -0.58
    POSITIVE LOGITS
     Tier
    0.65
     scaffolds
    0.63
    Tier
    0.61
     scaffold
    0.57
     Confer
    0.57
     scaffolding
    0.55
     tier
    0.55
    commodations
    0.53
     Scaffold
    0.52
     Lex
    0.50
    Activations Density 0.164%

    No Known Activations