© 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. 18-GEMMASCOPE-RES-16K
    11. 2519
    Prev
    Next
    INDEX
    Explanations

    terms associated with software licensing and conditions

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

    that precede "agreed" or "or"

    np_acts-logits-general · gemini-2.0-flash

    or agreed

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     even
    -0.72
     it
    -0.56
     vice
    -0.55
    windowFixed
    -0.53
     cap
    -0.50
     as
    -0.49
     not
    -0.48
     a
    -0.47
     be
    -0.47
    NameInMap
    -0.45
    POSITIVE LOGITS
    ंदीखरीदारी
    0.81
    SPJ
    0.72
    Personensuche
    0.69
    chach
    0.63
     cérami
    0.63
     ſche
    0.63
     ſever
    0.62
    yaszt
    0.61
     CMB
    0.59
     Majefty
    0.59
    Activations Density 0.174%

    No Known Activations