© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 12-GEMMASCOPE-RES-16K
    6. 1758
    Prev
    Next
    INDEX
    Explanations

    elements related to language localization and translation functionality

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_12/width_16k/average_l0_130
    Prompts (Dashboard)
    24,576 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
    findpost
    -0.78
    sizeCache
    -0.71
    رشف
    -0.68
    OGND
    -0.54
    WebVitals
    -0.53
     cref
    -0.53
    verwijspagina
    -0.53
    ConstraintMaker
    -0.49
    WriteTagHelper
    -0.48
     AssemblyTitle
    -0.47
    POSITIVE LOGITS
     languages
    0.78
     Languages
    0.76
     Language
    0.70
    Language
    0.69
     idiomas
    0.69
    Locale
    0.68
     lenguas
    0.68
     langues
    0.68
     language
    0.67
    Languages
    0.67
    Activations Density 0.330%

    No Known Activations