© 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. 8293
    Prev
    Next
    INDEX
    Explanations

    elements related to programming structure and organization

    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
    —
    -0.60
    WindowConstants
    -0.55
    (
    -0.54
    -(
    -0.54
    ("--
    -0.54
    clair
    -0.53
    —"
    -0.53
    -"
    -0.52
     cartão
    -0.51
    -$
    -0.50
    POSITIVE LOGITS
    \{\\
    0.79
    .*")]
    0.78
    GEBURTSDATUM
    0.74
     []:
    0.73
    存于互联网档案馆
    0.69
     الحره
    0.66
    UnknownFieldSet
    0.65
    //};
    0.63
    Tikang
    0.62
    findpost
    0.62
    Activations Density 0.114%

    No Known Activations