Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 19-GEMMASCOPE-RES-16K
    6. 11185
    Prev
    Next
    INDEX
    Explanations

    words indicating proximity or location in relation to other subjects or objects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     useDispatch
    -0.70
    hmigung
    -0.69
    BEA
    -0.67
    rrggbb
    -0.67
    webElementXpaths
    -0.66
    ]")]
    -0.64
    ագրություններ
    -0.63
    liferay
    -0.63
     chinois
    -0.63
    ("]");
    -0.62
    POSITIVE LOGITS
     around
    1.07
    Around
    1.02
    around
    0.99
     Around
    0.97
    AROUND
    0.96
     AROUND
    0.95
     torno
    0.86
     perimeter
    0.75
     corners
    0.73
     omkring
    0.71
    Activations Density 0.046%

    No Known Activations