© 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. 12-GEMMASCOPE-RES-16K
    6. 5643
    Prev
    Next
    INDEX
    Explanations

    mentions of technological products and their features

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_12/width_16k/average_l0_130
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    iprot
    -0.28
    quot
    -0.26
     pag
    -0.26
    sprintf
    -0.26
     am
    -0.25
     betweenstory
    -0.24
    Authors
    -0.24
    png
    -0.23
    ℉
    -0.23
    zarchiwizowane
    -0.23
    POSITIVE LOGITS
    featureID
    0.79
    windowFixed
    0.60
    PreferredItem
    0.60
    StoryboardSegue
    0.58
     modding
    0.57
    :✨
    0.57
    adena
    0.57
    RegressionTest
    0.56
    今度は
    0.56
     indígen
    0.56
    Activations Density 0.465%

    No Known Activations