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. 17-GEMMASCOPE-RES-16K
    6. 7046
    Prev
    Next
    INDEX
    Explanations

    scientific terms and phrases related to genetics and biological processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    脚注の使い方
    -0.80
    jsonwebtoken
    -0.75
    createCanvas
    -0.75
    存于互联网档案馆
    -0.70
     */;
    -0.69
    "]();
    -0.69
    Hochspringen
    -0.67
    Personensuche
    -0.67
     disambiguazione
    -0.67
     ());
    -0.67
    POSITIVE LOGITS
     are
    0.47
     is
    0.47
    لمين
    0.43
     hängen
    0.42
     sendok
    0.42
     can
    0.41
    ījum
    0.41
     aprendizagem
    0.40
     siguen
    0.40
     rafra
    0.39
    Activations Density 1.076%

    No Known Activations