© 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. 21-GEMMASCOPE-RES-16K
    11. 10983
    Prev
    Next
    INDEX
    Explanations

    token patterns and structural elements commonly found in programming languages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/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.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     oprot
    -0.59
    sidemargin
    -0.58
    InSection
    -0.57
     Domes
    -0.56
     brome
    -0.56
     ujednoznacz
    -0.56
    SequentialGroup
    -0.56
    RTEE
    -0.55
     pseud
    -0.53
     дописавши
    -0.52
    POSITIVE LOGITS
     casada
    0.44
     afectados
    0.44
     Konkurrenz
    0.43
     afectada
    0.43
     potência
    0.42
     senhora
    0.42
     antemano
    0.42
     ağır
    0.40
     atencion
    0.40
     apresentação
    0.40
    Activations Density 0.548%

    No Known Activations