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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 12-GEMMASCOPE-RES-16K
    6. 15959
    Prev
    Next
    INDEX
    Explanations

    code snippets or programming syntax

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 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
    Биография
    -0.81
    </em>
    -0.78
     “
    -0.74
    getRepository
    -0.69
    Sucesor
    -0.69
     مرئيه
    -0.67
     (“
    -0.63
    <em>
    -0.61
    لاث
    -0.61
    setAccessible
    -0.60
    POSITIVE LOGITS
    ```
    1.53
     cref
    1.05
     ```
    1.03
    +```
    1.01
    -```
    0.92
     purpoſe
    0.91
     Diſ
    0.86
     Monfieur
    0.84
    ijão
    0.83
     Centa
    0.82
    Activations Density 0.090%

    No Known Activations