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. 9338
    Prev
    Next
    INDEX
    Explanations

    specific identifiers, properties, and their corresponding values within programming code structures

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

    Code-related names and identifiers

    np_acts-logits-general · gemini-2.0-flash

    variable declarations ending in punctuation

    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
     propOrder
    -0.83
    كويكب
    -0.77
    "](
    -0.77
    )";
    
    -0.72
    )':
    -0.72
    ]";
    -0.70
    ISupport
    -0.68
    )":
    -0.67
    ),”
    -0.66
    <bos>
    -0.66
    POSITIVE LOGITS
    ?
    0.71
    ?;
    0.59
     None
    0.58
    ?:
    0.56
     ?
    0.56
    ?—
    0.56
    NULL
    0.53
    ;
    0.51
    ?.
    0.50
     none
    0.49
    Activations Density 0.145%

    No Known Activations