© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 31-GEMMASCOPE-RES-131K
    6. 24171
    Prev
    Next
    INDEX
    Explanations

    technical notation and formatting elements commonly used in programming or mathematical expressions

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

    code punctuation and syntax

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    AddTagHelper
    -0.67
     propOrder
    -0.65
    bootstrapcdn
    -0.56
     betweenstory
    -0.55
    OGND
    -0.55
    WriteTagHelper
    -0.51
    Columbia
    -0.51
     Columbia
    -0.49
    нгред
    -0.47
     Colombia
    -0.46
    POSITIVE LOGITS
     ProtoMessage
    0.39
     Oakland
    0.38
    readObject
    0.38
    فایل‌لار
    0.34
     Bakersfield
    0.34
    httphttps
    0.34
     Wolverhampton
    0.34
     Birmingham
    0.33
    ierungen
    0.33
     graças
    0.33
    Activations Density 0.000%

    No Known Activations