Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 22-GEMMASCOPE-RES-16K
    6. 16198
    Prev
    Next
    INDEX
    Explanations

    negations and expressions of limitations or boundaries

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

    negated by "not" or other negations

    np_acts-logits-general · gemini-2.0-flash

    not followed by verbs

    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
     duly
    -0.68
     variously
    -0.64
     presumably
    -0.59
     durchaus
    -0.57
    correctly
    -0.57
     correctly
    -0.55
     ändå
    -0.54
     realisation
    -0.54
    presumably
    -0.54
     lawfully
    -0.54
    POSITIVE LOGITS
    shortcuts
    0.79
     compromise
    0.74
    hésite
    0.68
     wasted
    0.64
    下载附件
    0.63
    Comprom
    0.63
     Compromise
    0.63
     rely
    0.62
    printStackTrace
    0.62
    RegressionTest
    0.62
    Activations Density 0.294%

    No Known Activations