© 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. 16-GEMMASCOPE-RES-16K
    11. 1215
    Prev
    Next
    INDEX
    Explanations

    references to categories or identifiers within structured data

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

    Hexadecimal characters

    np_acts-logits-general · gemini-2.0-flash

    hexadecimal strings with punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    脚注の使い方
    -0.81
     disambiguazione
    -0.81
     ModelExpression
    -0.81
     betweenstory
    -0.77
    Personendaten
    -0.77
     StringTokenizer
    -0.75
     estekak
    -0.75
     iſt
    -0.74
    ⓧ
    -0.70
    Diwedd
    -0.70
    POSITIVE LOGITS
    .
    0.53
    ,
    0.48
     
    0.45
     (
    0.44
     «
    0.43
    ăț
    0.42
    ecore
    0.41
     T
    0.41
     says
    0.41
    Say
    0.40
    Activations Density 0.142%

    No Known Activations