© 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-2-9B
    4. Residual Stream - 16k
    5. 41-GEMMASCOPE-RES-16K
    6. 6918
    Prev
    Next
    INDEX
    Explanations

    references to specific items or entities labeled with 'N' followed by numerical identifiers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 41-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_41/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.41.hook_resid_post
    Hook Layer
    41
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ampton
    -0.64
    которые
    -0.57
    foundland
    -0.52
    ympto
    -0.51
    ่า
    -0.49
    umberland
    -0.48
    melon
    -0.48
    存于互联网档案馆
    -0.45
    戬
    -0.43
    PDOException
    -0.43
    POSITIVE LOGITS
    onsense
    0.41
    n
    0.37
    l
    0.37
    RG
    0.36
    odal
    0.34
    ugget
    0.34
    PV
    0.34
    RM
    0.33
    atures
    0.33
    помним
    0.33
    Activations Density 0.260%

    No Known Activations