© 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-2-9B-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 374
    Prev
    Next
    INDEX
    Explanations

    terms related to participants or subjects in studies or research contexts

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

    "who" or "that" preceding a verb

    np_acts-logits-general · gemini-2.0-flash

    relative clauses with who/that

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 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
    .
    -0.34
     istore
    -0.33
    :
    -0.31
    another
    -0.29
    finally
    -0.28
     because
    -0.28
     tem
    -0.28
     finally
    -0.28
    yet
    -0.28
    Se
    -0.27
    POSITIVE LOGITS
    antMatchers
    0.69
    AndEndTag
    0.61
     ſhould
    0.60
     dieſe
    0.59
    arangay
    0.58
    ésultats
    0.58
    الحياه
    0.58
     dumne
    0.58
     ddelwed
    0.57
     beſte
    0.57
    Activations Density 0.688%

    No Known Activations