© 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. 1-GEMMASCOPE-RES-16K
    11. 4060
    Prev
    Next
    INDEX
    Explanations

    the word "never" and its variations to detect expressions of negation or exclusion

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    imab
    -0.61
    WEBPACK
    -0.60
    KommentareTeilen
    -0.57
    kı
    -0.57
    jooq
    -0.57
    posh
    -0.56
     Pristupljeno
    -0.56
    Біографія
    -0.56
    Kudos
    -0.56
     Kudos
    -0.56
    POSITIVE LOGITS
     never
    3.85
     Never
    3.60
    never
    3.58
    Never
    3.52
     NEVER
    3.24
    NEVER
    3.06
     nunca
    2.67
     Nunca
    2.56
     nigdy
    2.48
    Nunca
    2.41
    Activations Density 0.066%

    No Known Activations