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. 0-GEMMASCOPE-RES-16K
    6. 7852
    Prev
    Next
    INDEX
    Explanations

    references to a regulatory body or governing commission

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_0/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     betweenstory
    -0.86
    SizeF
    -0.74
     صوتيه
    -0.61
    RTLR
    -0.59
     arşivlendi
    -0.59
    astify
    -0.58
    webElementXpaths
    -0.57
    uxxxx
    -0.55
    Попис
    -0.54
     resourceCulture
    -0.54
    POSITIVE LOGITS
     commission
    0.76
     Commission
    0.72
    Cmd
    0.67
     Command
    0.67
    Command
    0.64
     command
    0.63
     challenging
    0.59
     cmd
    0.57
    Commission
    0.56
    cmd
    0.56
    Activations Density 0.338%

    No Known Activations