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 - 16k
    5. 8-GEMMASCOPE-RES-16K
    6. 38
    Prev
    Next
    INDEX
    Explanations

    phrases indicating desire or preference

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_8/width_16k/average_l0_99
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     carab
    -0.33
     muestre
    -0.33
    })]
    -0.32
     sientes
    -0.31
     cris
    -0.31
    calyp
    -0.30
     dist
    -0.30
     pal
    -0.29
     erup
    -0.29
     emo
    -0.29
    POSITIVE LOGITS
    aimerais
    0.69
     gostaria
    0.69
     gustaría
    0.67
    enumii
    0.67
    ⓧ
    0.66
     للمعارف
    0.63
     Administrativna
    0.61
    wish
    0.60
     möchte
    0.58
     BoxDecoration
    0.58
    Activations Density 0.134%

    No Known Activations