© 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. 8325
    Prev
    Next
    INDEX
    Explanations

    words related to deception or dishonesty

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

    ending in "-su" or starting with "un-", "in-", "or-"

    np_acts-logits-general · gemini-2.0-flash

    descriptive words from prefixes

    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
    RenderAtEndOf
    -0.63
     Pingback
    -0.57
     compris
    -0.56
    出版年
    -0.56
     fubject
    -0.54
    PrototypeOf
    -0.53
     referenties
    -0.53
    attore
    -0.53
    onAttach
    -0.50
     laſt
    -0.49
    POSITIVE LOGITS
    ingly
    0.61
     enough
    0.60
    AddHtmlAttribute
    0.60
     profoundly
    0.57
    มาะ
    0.57
    Embeddable
    0.57
    agoza
    0.57
     näky
    0.56
    rabaya
    0.56
    fulness
    0.56
    Activations Density 0.213%

    No Known Activations