Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 10505
    Prev
    Next
    INDEX
    Explanations

    expressions of excitement or strong emotional reactions

    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
    帖最后由
    -0.48
    
    -0.41
     $\&$
    -0.38
    wapV
    -0.38
    mobileqq
    -0.38
    twimg
    -0.36
    +"&
    -0.36
    咱们
    -0.35
    +};
    -0.34
     zijne
    -0.34
    POSITIVE LOGITS
    aaa
    0.97
    iii
    0.96
    aa
    0.95
    hhh
    0.94
    hhhh
    0.94
    aaaaa
    0.94
    aaaa
    0.93
    aaaaaa
    0.91
    hhhhh
    0.91
    hh
    0.91
    Activations Density 0.251%

    No Known Activations