© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 9-GEMMASCOPE-RES-16K
    6. 2651
    Prev
    Next
    INDEX
    Explanations

    terms related to wind conditions and their effects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    addPreferredGap
    -0.84
     Lush
    -0.69
    toMatchSnapshot
    -0.68
    عط
    -0.65
     McCoy
    -0.64
    sightly
    -0.64
     Darmstadt
    -0.64
     Administrativna
    -0.64
     ProtoMessage
    -0.63
    orious
    -0.63
    POSITIVE LOGITS
     wind
    1.74
     Wind
    1.73
    Wind
    1.70
    wind
    1.69
     WIND
    1.64
     winds
    1.60
     Winds
    1.52
    winds
    1.49
    WIND
    1.49
     viento
    1.32
    Activations Density 0.045%

    No Known Activations