© 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. 5-GEMMASCOPE-RES-16K
    6. 476
    Prev
    Next
    INDEX
    Explanations

    strings formatted as question or answer indicators, specifically in relation to parameters in code or data

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

    punctuation marks utilized in programming or coding syntax, particularly colons and parentheses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    leneck
    -0.78
     AssemblyCulture
    -0.73
     rowspan
    -0.72
    vací
    -0.60
    dema
    -0.60
     Inc
    -0.60
     mellitus
    -0.58
    ‬
    -0.58
    ב
    -0.57
    teng
    -0.57
    POSITIVE LOGITS
    :"
    1.56
    :'
    1.54
    :”
    1.48
    :\
    1.44
    :-
    1.44
    :<
    1.41
    :{
    1.41
    :+
    1.40
    :[
    1.39
    :?
    1.36
    Activations Density 0.035%

    No Known Activations