© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 131k
    9. 24-GEMMASCOPE-RES-131K
    11. 323
    Prev
    Next
    INDEX
    Explanations

    elements related to mathematical operations and programming syntax

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

    bit shifts and bitwise AND operations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_131k/average_l0_97
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    falgar
    -0.57
    ={`/
    -0.56
     パンチラ
    -0.52
    ſſung
    -0.52
    éns
    -0.52
     tslint
    -0.51
    𑄴
    -0.51
    <pad>
    -0.51
    <unused8>
    -0.51
    <unused17>
    -0.51
    POSITIVE LOGITS
     above
    0.47
     citada
    0.40
    AddHtmlAttribute
    0.36
     mencionados
    0.36
     powy
    0.36
     appunto
    0.35
    上記の
    0.35
    RetentionPolicy
    0.34
     aforesaid
    0.34
    上記
    0.34
    Activations Density 0.021%

    No Known Activations