© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 13605
    Prev
    Next
    INDEX
    Explanations

    phrases or references to local businesses and service offerings, particularly related to flowers

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

    punctuation marks and special characters that serve as delimiters or separators in structured text.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    iro
    -0.40
     ${\
    -0.34
     Holman
    -0.34
     ...
    -0.33
    łecz
    -0.31
    <?
    -0.31
    <?=$
    -0.31
    zi
    -0.30
    ello
    -0.29
    ${\
    -0.29
    POSITIVE LOGITS
     Wikimedijinoj
    0.82
    principalTable
    0.81
     GenerationType
    0.81
    yntaxException
    0.74
    awtextra
    0.72
    enderror
    0.71
    IntoConstraints
    0.71
    setVerticalGroup
    0.67
    Rujuakan
    0.66
    PostBack
    0.66
    Activations Density 1.288%

    No Known Activations