© 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-2-9B
    7. Residual Stream - 16k
    9. 31-GEMMASCOPE-RES-16K
    11. 5967
    Prev
    Next
    INDEX
    Explanations

    elements related to website navigation and layout

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    HTML and web framework markup code (Bootstrap navigation bars, CSS styling, and related web development syntax).

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Datuak
    -0.94
     виправивши
    -0.77
     становника
    -0.70
    الحياه
    -0.69
     يتيمه
    -0.68
    Спасылкі
    -0.66
    istoitu
    -0.66
    BagConstraints
    -0.65
    IVEREF
    -0.63
    expandindo
    -0.60
    POSITIVE LOGITS
    --)
    0.37
     însă
    0.34
    "));
    0.33
    googleapis
    0.33
     });
    0.32
     ]
    0.32
    selenium
    0.32
    ętr
    0.31
     Flea
    0.29
     BitmapFactory
    0.29
    Activations Density 0.417%

    No Known Activations