© 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-IT
    7. Residual Stream - 131k
    9. 9-GEMMASCOPE-RES-131K
    11. 84172
    Prev
    Next
    INDEX
    Explanations

    issues related to code functionality and troubleshooting

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

    not working or appearing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     utafitiHapana
    -0.61
     onCancelled
    -0.60
    脚注の使い方
    -0.59
     resourceCulture
    -0.59
    +#+#
    -0.57
    numerusform
    -0.56
     meriva
    -0.56
    Demografie
    -0.54
     avoient
    -0.53
     disambiguazione
    -0.53
    POSITIVE LOGITS
    теристи
    0.30
    complexContent
    0.28
    とん
    0.28
    unknownFields
    0.27
     VERY
    0.27
    grounds
    0.26
    ¡¡¡
    0.25
    isContained
    0.24
    illigen
    0.24
     ADDITIONAL
    0.24
    Activations Density 0.338%

    No Known Activations