© 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. 5-GEMMASCOPE-RES-16K
    11. 9605
    Prev
    Next
    INDEX
    Explanations

    negations and expressions of not being or lacking something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    <bos>
    -0.92
    er
    -0.74
     Weiss
    -0.73
    rete
    -0.72
    AOS
    -0.69
     Blanchard
    -0.67
    तः
    -0.66
     cartes
    -0.65
     Ballard
    -0.65
     pary
    -0.65
    POSITIVE LOGITS
     isn
    1.64
     wasn
    1.48
     weren
    1.42
     shouldn
    1.42
     Isn
    1.42
     hasn
    1.41
     aren
    1.41
     Wasn
    1.40
     doesn
    1.39
     didn
    1.36
    Activations Density 0.061%

    No Known Activations