© 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. 13072
    Prev
    Next
    INDEX
    Explanations

    technical and legal terminology along with references to specific organizations and codes

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

    Follows a period, backslash, or number

    np_acts-logits-general · gemini-2.0-flash

    legal cases and statutes

    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
    tagext
    -0.53
    SourceChecksum
    -0.52
     SwitchCompat
    -0.50
    NameInMap
    -0.48
    qtype
    -0.47
    ніципалі
    -0.47
     Icarus
    -0.46
     Administrativna
    -0.45
    wendi
    -0.44
     travaillons
    -0.43
    POSITIVE LOGITS
     HasFactory
    0.67
     Paglinawan
    0.63
    ponses
    0.59
    UnitTesting
    0.59
     المعيارى
    0.57
     sportback
    0.57
    ̣ng
    0.55
     UIAlert
    0.55
     AA
    0.54
    Referanser
    0.52
    Activations Density 0.636%

    No Known Activations