© 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. 10644
    Prev
    Next
    INDEX
    Explanations

    locations or contexts indicated by the word "where"

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

    "Where" followed by a pronoun

    np_acts-logits-general · gemini-2.0-flash

    "where" followed by describing clauses

    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
     barbati
    -0.55
     faber
    -0.54
    them
    -0.53
     deschis
    -0.52
     őket
    -0.49
     bēr
    -0.49
    ējās
    -0.49
     način
    -0.48
     sobą
    -0.48
     folosit
    -0.47
    POSITIVE LOGITS
     they
    1.26
     we
    1.15
     it
    1.00
     you
    0.97
     there
    0.96
     he
    0.92
    帖最后由
    0.91
    )"),
    0.83
    __':
    0.82
    '},
    0.81
    Activations Density 0.159%

    No Known Activations