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. 8-GEMMASCOPE-RES-16K
    6. 4682
    Prev
    Next
    INDEX
    Explanations

    structural elements or coding syntax related to programming or technical documentation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    κτήθηκε
    -0.54
     nonUne
    -0.53
     sarili
    -0.52
     gant
    -0.51
     AppColors
    -0.50
    endpush
    -0.50
    DoubleQuotes
    -0.50
    ৎ
    -0.50
     sawing
    -0.50
    ENDIF
    -0.50
    POSITIVE LOGITS
    <bos>
    0.77
     الحره
    0.74
    ArrowToggle
    0.73
    WriteTagHelper
    0.66
    ########.
    0.64
    MigrationBuilder
    0.60
    InjectAttribute
    0.58
     تانيه
    0.57
     <=",
    0.56
    StoryboardSegue
    0.56
    Activations Density 0.393%

    No Known Activations