© 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-2-9B
    7. Residual Stream - 16k
    9. 35-GEMMASCOPE-RES-16K
    11. 12822
    Prev
    Next
    INDEX
    Explanations

    elements of mathematical notation and calculations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 35-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_35/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.35.hook_resid_post
    Hook Layer
    35
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ſind
    -0.99
    ロウィン
    -0.97
     ſever
    -0.93
    iſchen
    -0.90
     ſch
    -0.90
     zwiſchen
    -0.88
     geſch
    -0.88
     ſche
    -0.88
     ſei
    -0.87
     beſte
    -0.87
    POSITIVE LOGITS
    ↵↵
    0.29
    s
    0.29
    ing
    0.29
    er
    0.27
    r
    0.26
    ere
    0.26
    。
    0.26
    w
    0.25
    ill
    0.25
     Q
    0.25
    Activations Density 0.193%

    No Known Activations