© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 5539
    Prev
    Next
    INDEX
    Explanations

    emotional expressions and conflicts related to authority

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

    before or related to "world"

    np_acts-logits-general · gemini-2.0-flash

    celestial Duo, Dan world, emperor

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     exactly
    -0.44
     (
    -0.42
     nø
    -0.41
     exact
    -0.35
     tæ
    -0.34
     especially
    -0.34
     inwest
    -0.33
     Verordnung
    -0.33
    如果有
    -0.33
    exactly
    -0.32
    POSITIVE LOGITS
    setVerticalGroup
    0.84
    parsedMessage
    0.77
    expandindo
    0.76
     Administrativna
    0.75
    AddTagHelper
    0.74
    abestanden
    0.69
    CppMethod
    0.68
    postsleuth
    0.68
    Ӕ
    0.66
     wireType
    0.66
    Activations Density 0.092%

    No Known Activations