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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 11336
    Prev
    Next
    INDEX
    Explanations

    HTML structure and elements related to forms and navigation

    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
    تقاوى
    -0.71
    +#+#
    -0.65
    Hochspringen
    -0.55
    loe
    -0.54
     ujednoznacz
    -0.53
    Clik
    -0.53
    [++
    -0.51
     INTERESAR
    -0.49
    wpdb
    -0.49
    Bindable
    -0.47
    POSITIVE LOGITS
    potranspiration
    0.61
    RegistryLite
    0.59
    }`;
    0.58
    millimeters
    0.58
    ]";
    0.57
    }\]
    0.57
     Wicidata
    0.57
     Drapeau
    0.56
    )";
    
    0.54
     comuniques
    0.54
    Activations Density 0.048%

    No Known Activations