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. 10-GEMMASCOPE-RES-16K
    6. 2909
    Prev
    Next
    INDEX
    Explanations

    references to native and indigenous species or concepts

    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
    #+#
    -0.92
     SqlCommand
    -0.88
    ValueStyle
    -0.81
     Réponses
    -0.74
    coroutines
    -0.70
     considérons
    -0.69
    LEncoder
    -0.69
    isSuccessful
    -0.68
     Hezbollah
    -0.68
    chism
    -0.67
    POSITIVE LOGITS
    Native
    1.26
     Native
    1.25
     native
    1.20
     nativo
    1.16
     natives
    1.10
    NATIVE
    1.10
     Natives
    1.06
    native
    1.04
     nativa
    1.04
    nati
    0.90
    Activations Density 0.083%

    No Known Activations