© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 1860
    Prev
    Next
    INDEX
    Explanations

    elements related to coding, particularly focusing on search functionalities and data retrieval

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

    programming-related terms and actions involving searching, matching, processing, or retrieving results.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
     TAMBIÉN
    -0.39
     zorg
    -0.35
    hdc
    -0.34
    RTSN
    -0.34
     Harmon
    -0.34
    aarrggbb
    -0.34
    harmon
    -0.33
    必要
    -0.32
    новништво
    -0.32
     Ajoutez
    -0.32
    POSITIVE LOGITS
    rinfo
    0.73
     snippetHide
    0.55
     responders
    0.53
    BindingResult
    0.52
     Exacts
    0.52
     candidates
    0.50
    SBATCH
    0.50
    BibitemShut
    0.49
     Audiodateien
    0.49
     <=",
    0.49
    Activations Density 0.337%

    No Known Activations