© 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. 4417
    Prev
    Next
    INDEX
    Explanations

    syntax elements and structures used in programming languages

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

    programming-related tokens and syntax elements, particularly in code parsing and switch statements.

    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
    expandindo
    -0.69
     &___
    -0.64
    MessageTagHelper
    -0.63
    ########.
    -0.60
    IVEREF
    -0.57
    исленность
    -0.54
    addCriterion
    -0.53
    Демографія
    -0.50
     Autorizaciones
    -0.48
     surla
    -0.47
    POSITIVE LOGITS
    SequentialGroup
    0.49
    Erreferentziak
    0.46
    TableAdapter
    0.41
    A
    0.41
    Referencie
    0.38
     HasFactory
    0.38
    Referencer
    0.38
     when
    0.37
     perhaps
    0.37
    if
    0.37
    Activations Density 0.200%

    No Known Activations