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-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 2743
    Prev
    Next
    INDEX
    Explanations

    code snippets and related programming elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Code snippets with outputs or parameters

    np_acts-logits-general · gemini-2.0-flash

    explanatory statements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    |}{$
    -0.69
     utafitiHapana
    -0.68
    ```
    
    -0.68
    __(/*!
    -0.66
    URLException
    -0.66
    -
    
    -0.62
    SPATH
    -0.59
    ATURE
    -0.56
    
    -0.55
    \\
    
    -0.55
    POSITIVE LOGITS
     Note
    1.03
    Note
    1.02
    Clearly
    0.94
    These
    0.92
    note
    0.90
     Clearly
    0.90
    Notice
    0.85
     These
    0.85
     note
    0.84
    Obviously
    0.83
    Activations Density 0.483%

    No Known Activations