© 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. 3652
    Prev
    Next
    INDEX
    Explanations

    terminology and elements related to programming and function definitions

    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
    zzleHttp
    -0.63
     ब्रेकडाउन
    -0.58
    migrationBuilder
    -0.56
    httphttps
    -0.53
    saraba
    -0.53
     roux
    -0.52
    PreferredItem
    -0.50
    WebVitals
    -0.49
     ComVisible
    -0.49
     Rockies
    -0.49
    POSITIVE LOGITS
     Scheme
    0.63
     clo
    0.62
     Rack
    0.62
     cdr
    0.61
     car
    0.60
     Clo
    0.60
     Lisp
    0.59
    gens
    0.58
     atom
    0.58
     CDR
    0.58
    Activations Density 0.420%

    No Known Activations