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. 20-GEMMASCOPE-RES-16K
    6. 1447
    Prev
    Next
    INDEX
    Explanations

    HTML attributes related to sourcing scripts and styles

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

    HTML attributes: src and href

    np_acts-logits-general · gemini-2.0-flash

    HTML src and href attributes

    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
    +:+
    -0.54
     нами
    -0.47
    })));
    -0.47
    TRA
    -0.46
    παν
    -0.45
    жды
    -0.43
    Życiorys
    -0.42
    ➟
    -0.42
    paraíso
    -0.42
     le
    -0.42
    POSITIVE LOGITS
    XmlAccessorType
    0.67
     كومونز
    0.66
    UserScript
    0.66
     CreateTagHelper
    0.64
    centages
    0.63
     initWithFrame
    0.61
     BoxDecoration
    0.61
    bootstrapcdn
    0.61
     للمعارف
    0.60
    contentLoaded
    0.60
    Activations Density 0.036%

    No Known Activations