© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 12-GEMMASCOPE-RES-16K
    11. 14519
    Prev
    Next
    INDEX
    Explanations

    specific terms related to scientific or technical concepts within various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    fjspx
    -0.86
     Италијани
    -0.82
    AndEndTag
    -0.81
     للاسماء
    -0.81
     ModelExpression
    -0.79
     AssemblyCulture
    -0.76
     kaarangay
    -0.76
    Personendaten
    -0.75
    complexContent
    -0.73
    OGND
    -0.70
    POSITIVE LOGITS
    scriptcase
    0.49
    -------
    0.48
    miyorum
    0.47
     daya
    0.43
     amore
    0.43
    ç
    0.43
     Easy
    0.40
    erto
    0.37
    ings
    0.37
    erre
    0.37
    Activations Density 1.642%

    No Known Activations