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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 131k
    5. 24-GEMMASCOPE-RES-131K
    6. 792
    Prev
    Next
    INDEX
    Explanations

    chemical or pharmacological terms related to medications and compounds

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

    Supra shoes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_131k/average_l0_97
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
     AppComponent
    -0.34
     knap
    -0.31
    IComponent
    -0.30
     alcanzar
    -0.28
    Composable
    -0.28
     jScrollPane
    -0.27
     đồ
    -0.27
    ధ
    -0.26
    UDAD
    -0.26
     maximum
    -0.26
    POSITIVE LOGITS
    uxxxx
    0.67
    httphttps
    0.64
    Precalculus
    0.63
     Мексичка
    0.60
    mybatisplus
    0.59
    bootstrapcdn
    0.59
    __*/
    0.57
     referrerpolicy
    0.57
     typelib
    0.56
    Билгалдахарш
    0.56
    Activations Density 0.004%

    No Known Activations