© 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. 21-GEMMASCOPE-RES-16K
    11. 2221
    Prev
    Next
    INDEX
    Explanations

    conjunctions and transitional phrases used to connect thoughts or clauses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    writeFieldEnd
    -0.72
     unknownFields
    -0.68
     autorytatywna
    -0.63
     betweenstory
    -0.57
    elemField
    -0.55
     TestBed
    -0.55
     AssemblyCulture
    -0.54
    zzleHttp
    -0.54
    الإنجليزية
    -0.54
    Portale
    -0.54
    POSITIVE LOGITS
     remember
    1.86
     beware
    1.71
     Beware
    1.53
    Beware
    1.45
     Remember
    1.44
    remember
    1.42
    Remember
    1.41
     be
    1.39
     note
    1.38
     ensure
    1.36
    Activations Density 0.304%

    No Known Activations