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. 4118
    Prev
    Next
    INDEX
    Explanations

    data structures and their components related to programming or algorithmic concepts

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

    Mathematical/scientific notation and symbols

    np_acts-logits-general · gemini-2.0-flash

    LaTeX math delimiters

    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
    })));
    -0.64
     مرئيه
    -0.64
    ']")
    -0.60
    atrième
    -0.58
    зулта
    -0.54
     Kole
    -0.53
    }")]
    -0.53
    ">',
    -0.51
    RenderAtEndOf
    -0.51
    "))
    
    -0.50
    POSITIVE LOGITS
    Geplaatst
    0.73
    AxisAlignment
    0.72
    addCriterion
    0.69
    principalColumn
    0.67
     acceptez
    0.66
    ChildScrollView
    0.66
     consultato
    0.65
    CGRectMake
    0.64
    viewWillAppear
    0.63
     sumpay
    0.62
    Activations Density 0.714%

    No Known Activations