© 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-2-2B
    4. Residual Stream - 16k
    5. 18-GEMMASCOPE-RES-16K
    6. 1682
    Prev
    Next
    INDEX
    Explanations

    elements related to mathematical and scientific expressions

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

    Code, math, or right-related terms

    np_acts-logits-general · gemini-2.0-flash

    right and left

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     lesser
    -0.78
     мень
    -0.74
     smaller
    -0.67
    Minor
    -0.66
    Less
    -0.63
    LowerCase
    -0.63
     Less
    -0.63
     Minder
    -0.62
     less
    -0.62
    minor
    -0.62
    POSITIVE LOGITS
    topRight
    0.73
    EndProject
    0.72
    posedge
    0.71
    right
    0.71
    ThroughAttribute
    0.71
     right
    0.70
     upper
    0.70
     Upper
    0.69
    getRight
    0.69
    دانشنامهٔ
    0.68
    Activations Density 0.391%

    No Known Activations