© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 7246
    Prev
    Next
    INDEX
    Explanations

    elements related to educational strategies and student assessment

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

    Text within brackets/parentheses

    np_acts-logits-general · gemini-2.0-flash

    semicolon termination

    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
    ":
    -0.84
    "):
    -0.78
    ':
    -0.77
     OMITBAD
    -0.75
    '):
    -0.72
    __':
    -0.71
    __":
    -0.70
    ")){
    -0.70
    .")
    -0.67
    smithy
    -0.65
    POSITIVE LOGITS
    ;
    1.67
     ;
    1.32
    ；
    1.32
    ?;
    1.31
    /;
    1.23
     ;
    1.12
    °;
    1.11
    %;
    1.10
    ؛
    1.09
    !;
    1.09
    Activations Density 1.556%

    No Known Activations