© 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. 7569
    Prev
    Next
    INDEX
    Explanations

    specific combinations and frequencies of characters and symbols

    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
     الرياضيه
    -0.46
    \{\\
    -0.45
     betweenstory
    -0.45
    脚注の使い方
    -0.39
    currentItem
    -0.39
    versiti
    -0.38
     XNUMX
    -0.35
    esModule
    -0.34
    nestjs
    -0.34
    NUMX
    -0.33
    POSITIVE LOGITS
     word
    0.55
    oooooooo
    0.54
    iiiiiiii
    0.53
    oooo
    0.53
    oooooo
    0.52
    UUUU
    0.52
    OOOOOOOO
    0.51
    oooooooooooooooo
    0.51
    OOOO
    0.51
    *
    0.50
    Activations Density 0.337%

    No Known Activations