© 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-2-2B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 5368
    Prev
    Next
    INDEX
    Explanations

    discussions about resource allocation and spending efficiency

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

    the use of resources

    np_acts-logits-general · gemini-2.0-flash

    time or money spent

    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
    protoc
    -0.72
    mergeFrom
    -0.68
    WriteLiteral
    -0.63
    igte
    -0.58
     OMITBAD
    -0.57
    évaluateur
    -0.55
     مواليد
    -0.55
    principalColumn
    -0.54
    Aiheesta
    -0.54
    +#+#
    -0.53
    POSITIVE LOGITS
     spent
    2.14
     devoted
    1.74
     Spent
    1.71
     spend
    1.71
    spent
    1.66
     dedicated
    1.61
     Spend
    1.53
     spends
    1.48
     dedicate
    1.46
     devote
    1.45
    Activations Density 0.333%

    No Known Activations