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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 5-GEMMASCOPE-RES-16K
    11. 9184
    Prev
    Next
    INDEX
    Explanations

    specific types of punctuation and formatting associated with legal or technical documents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     iprot
    -0.62
    ")));
    -0.52
     hinaus
    -0.49
    acyjnych
    -0.48
     Giappone
    -0.48
    ]").
    -0.47
    Gdx
    -0.46
     poroz
    -0.45
     Canadá
    -0.45
     megal
    -0.43
    POSITIVE LOGITS
    󠁢
    0.82
    wapV
    0.79
    istoitu
    0.76
    DockStyle
    0.75
     تضيفلها
    0.75
    InternalFrame
    0.75
     onAnimation
    0.74
     TextAlign
    0.73
    OGND
    0.71
     objectAtIndex
    0.69
    Activations Density 0.539%

    No Known Activations