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. 1719
    Prev
    Next
    INDEX
    Explanations

    code elements related to object properties and their attributes

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

    Code, URLs, and raw data

    np_acts-logits-general · gemini-2.0-flash

    technical terms and code elements

    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
    "]);
    -0.88
    "]))
    -0.85
    ])));
    -0.85
    ()]);
    -0.84
    )))));
    -0.84
    "])
    
    -0.83
    ])))
    -0.83
    "]));
    -0.83
    _));
    -0.82
    "));
    -0.82
    POSITIVE LOGITS
     Reverso
    0.65
     varargin
    0.59
     Répondre
    0.59
    醐
    0.52
    phard
    0.51
     interacting
    0.51
    atteindre
    0.51
     himſelf
    0.51
    iség
    0.50
     orgánica
    0.49
    Activations Density 0.174%

    No Known Activations