© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 15-GEMMASCOPE-RES-16K
    11. 12480
    Prev
    Next
    INDEX
    Explanations

    elements related to the structure and formatting of messages or documents

    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
    expandindo
    -0.78
    __":
    -0.77
    __':
    -0.70
     виправивши
    -0.68
    __":
    -0.67
    )}</
    -0.66
    `;
    -0.66
     tartalomajánló
    -0.66
    ?')
    -0.65
    ']))
    -0.64
    POSITIVE LOGITS
     ويكيميديا
    0.66
     disambiguazione
    0.63
    AsUp
    0.57
    chapper
    0.57
     brevis
    0.55
     Armani
    0.53
     פני
    0.53
    LogFactory
    0.52
     generalization
    0.50
     udaler
    0.49
    Activations Density 1.494%

    No Known Activations