© 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-2-9B
    4. Residual Stream - 16k
    5. 36-GEMMASCOPE-RES-16K
    6. 7712
    Prev
    Next
    INDEX
    Explanations

    references to solutions or problem-solving in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 36-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_36/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.36.hook_resid_post
    Hook Layer
    36
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     vectorielle
    -0.45
    getKeyCode
    -0.36
    glTranslatef
    -0.36
    CodeDom
    -0.34
    Schedulers
    -0.32
     vectorielles
    -0.32
     coals
    -0.32
     било
    -0.32
    rand
    -0.32
    fcntl
    -0.31
    POSITIVE LOGITS
     Provider
    0.63
     HasFactory
    0.62
     Providers
    0.58
     方案
    0.58
     provider
    0.57
     Solution
    0.55
    RegressionTest
    0.54
     providers
    0.52
    SBATCH
    0.50
     disambiguazione
    0.50
    Activations Density 0.119%

    No Known Activations