© 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. 22-GEMMASCOPE-RES-16K
    11. 9095
    Prev
    Next
    INDEX
    Explanations

    the word "never" and its variations in different contexts

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

    Sentences starting with "never"

    np_acts-logits-general · gemini-2.0-flash

    never followed by a verb

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    TypedDataSet
    -0.94
     engraçadas
    -0.81
    dafx
    -0.77
    StateToProps
    -0.75
    '])->
    -0.75
    ]")]
    -0.75
    :]:
    -0.74
    حياتها
    -0.73
    حياته
    -0.73
    లాలు
    -0.73
    POSITIVE LOGITS
     again
    0.79
     really
    0.77
     once
    0.77
    ending
    0.76
    more
    0.74
    mind
    0.69
    theless
    0.69
     truly
    0.68
     before
    0.66
     Again
    0.64
    Activations Density 0.065%

    No Known Activations