© 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. 20-GEMMASCOPE-RES-16K
    11. 16159
    Prev
    Next
    INDEX
    Explanations

    concepts related to cellular processes, particularly those involving disruptions in function and their consequences

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

    cause and effect

    np_acts-logits-general · gemini-2.0-flash

    predicting consequences or results

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 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
    حيح
    -0.55
    IsInitialized
    -0.55
    RTGC
    -0.55
    titleMargin
    -0.53
    Mixin
    -0.51
    jgl
    -0.50
     nargin
    -0.49
    ngdoc
    -0.47
    Jîn
    -0.46
    回戦
    -0.46
    POSITIVE LOGITS
     resulted
    1.95
     resulting
    1.78
     lead
    1.66
     result
    1.63
    resulting
    1.62
     leading
    1.49
     leads
    1.47
    lead
    1.45
     Result
    1.41
    result
    1.37
    Activations Density 0.973%

    No Known Activations