© 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. 2940
    Prev
    Next
    INDEX
    Explanations

    HTML closing tags and associated syntax elements

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

    HTML closing tags

    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
    s
    -0.74
    enging
    -0.73
     Bana
    -0.69
     Mendel
    -0.68
    bentar
    -0.68
    yethylene
    -0.67
    bege
    -0.67
    Royce
    -0.67
    solr
    -0.67
     McAfee
    -0.67
    POSITIVE LOGITS
    </th>
    1.05
     pleaſure
    0.95
    ſelf
    0.93
     ſy
    0.93
     ſind
    0.92
     Theſe
    0.89
     Inſ
    0.89
     Oester
    0.88
     beſt
    0.88
     Reſ
    0.87
    Activations Density 0.125%

    No Known Activations