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. 4-GEMMASCOPE-RES-16K
    6. 3513
    Prev
    Next
    INDEX
    Explanations

    expressions of hope and encouragement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ThemeData
    -0.54
    ```
    -0.53
    nicas
    -0.52
    chauer
    -0.52
    SerializeField
    -0.52
    moveToFirst
    -0.51
     timp
    -0.49
    transQ
    -0.49
    cije
    -0.49
    manas
    -0.49
    POSITIVE LOGITS
     hope
    1.80
     hoped
    1.62
     hopes
    1.57
     hoping
    1.57
     Hope
    1.55
    Hope
    1.52
    hope
    1.51
    Hopefully
    1.49
     Hopefully
    1.47
     Hoping
    1.45
    Activations Density 0.160%

    No Known Activations