© 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 - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 104651
    Prev
    Next
    INDEX
    Explanations

    questions related to mathematical operations, such as calculating factors and remainders

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

    Question phrases in mathematical problems that request calculations of remainders after division or identification of prime factors of variables.

    eleuther_acts_top20 · claude-3-7-sonnet-20250219Triggered by @lu-christina
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    MLLoader
    -0.69
    +#+#
    -0.68
    MessageState
    -0.62
    رشف
    -0.62
     protoimpl
    -0.60
    ConstraintMaker
    -0.58
    AddTagHelper
    -0.58
    SourceChecksum
    -0.57
    contentLoaded
    -0.57
    articolo
    -0.57
    POSITIVE LOGITS
    Biografía
    0.30
    PullParser
    0.29
    英
    0.27
    <eos>
    0.25
     particular
    0.25
     تضيفلها
    0.25
     suất
    0.25
     preval
    0.24
     Espec
    0.24
    SOUNDBITE
    0.23
    Activations Density 0.077%

    No Known Activations