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. 1699
    Prev
    Next
    INDEX
    Explanations

    bracket and brace notations used in programming or mathematical expressions

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

    Code snippets with brackets and parentheses

    np_acts-logits-general · gemini-2.0-flash

    closing braces and parentheses

    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
     estekak
    -0.65
     '\\;'
    -0.60
     кӀ
    -0.51
    ecap
    -0.51
    AsUp
    -0.51
     voca
    -0.49
    hynchus
    -0.49
    oredCriteria
    -0.48
    ็จ
    -0.48
    kuuta
    -0.48
    POSITIVE LOGITS
     }}$}
    0.79
    }\}
    0.71
    })$}
    0.70
    BeginInit
    0.69
    ")}
    0.67
    ]")]
    0.62
    StackNavigator
    0.60
    ]}"
    0.60
    ()}}
    0.59
    ).]
    0.59
    Activations Density 0.055%

    No Known Activations