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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 8177
    Prev
    Next
    INDEX
    Explanations

    specific programming and technical terms or phrases related to coding and software documentation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Technical and programming-related terms in multilingual web content, including code syntax, error messages, and documentation elements.

    eleuther_acts_top20 · claude-3-7-sonnet-20250219Triggered by @lu-christina
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     للمعارف
    -0.51
     kaynağından
    -0.39
    AutoScaleMode
    -0.34
     виправивши
    -0.33
     transfieras
    -0.32
     مرئيه
    -0.31
     محفوظة
    -0.31
    tagHelperRunner
    -0.31
    styleType
    -0.29
    GTCX
    -0.28
    POSITIVE LOGITS
     Infór
    0.76
    الدراسه
    0.69
    HomeAsUpEnabled
    0.68
     informée
    0.66
    MemoryWarning
    0.65
     Infórmanos
    0.63
     препратки
    0.60
    pecabe
    0.59
     Tourisme
    0.59
    tênis
    0.59
    Activations Density 0.099%

    No Known Activations