© 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. 13606
    Prev
    Next
    INDEX
    Explanations

    HTML header tags and their hierarchy within the document structure

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

    HTML and markdown heading tags (h1, h2, h3, h4).

    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
     Stra
    -0.40
     ind
    -0.38
     Because
    -0.38
    KATH
    -0.36
    モチーフ
    -0.36
     because
    -0.36
    راف
    -0.36
    favourable
    -0.36
    Because
    -0.36
    idx
    -0.36
    POSITIVE LOGITS
    <h2>
    0.69
    httphttps
    0.65
    adaptiveStyles
    0.57
     MainAxisSize
    0.56
    </thead>
    0.56
    AnimationsModule
    0.56
     OnEnable
    0.56
     utafitiHapana
    0.55
    __*/
    0.53
    Hochspringen
    0.52
    Activations Density 0.029%

    No Known Activations