© 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. 15-GEMMASCOPE-RES-16K
    6. 2937
    Prev
    Next
    INDEX
    Explanations

    specific measurements and quantities in scientific contexts

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

    numerical values related to measurements and calculations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ⓧ
    -0.63
    клопе
    -0.55
    __).
    -0.51
    mazoo
    -0.47
    <bos>
    -0.46
    sidemargin
    -0.45
    DoNot
    -0.44
    >>()
    -0.44
    >')
    -0.43
    '))
    
    -0.43
    POSITIVE LOGITS
    ListItemIcon
    0.76
    expandindo
    0.67
    Rhestr
    0.62
    addCriterion
    0.60
     iprot
    0.60
     StringTokenizer
    0.60
    Diweddarwch
    0.59
    titleMargin
    0.59
    interopRequire
    0.57
    yntaxException
    0.56
    Activations Density 0.444%

    No Known Activations