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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 10-GEMMASCOPE-RES-16K
    6. 2763
    Prev
    Next
    INDEX
    Explanations

    terms related to downloading files and utilizing software services, especially in a technical or digital context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/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.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     rep
    -0.53
     den
    -0.44
     http
    -0.43
     re
    -0.43
     tri
    -0.42
    País
    -0.41
     ext
    -0.41
    GEBURTS
    -0.40
     ret
    -0.39
     simplifié
    -0.39
    POSITIVE LOGITS
    ReusableCell
    0.87
    EndInit
    0.82
     Référence
    0.81
     Majefty
    0.81
     Diſ
    0.79
     contextLoads
    0.78
    Демографія
    0.77
     Jefus
    0.77
     Monfieur
    0.76
     beginnetje
    0.75
    Activations Density 0.166%

    No Known Activations