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

    Neuronpedia

    Jacobian LensNEW
    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. 36019
    Prev
    Next
    INDEX
    Explanations

    phrases related to relationships and a sense of obligation

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

    describes purpose or characteristic

    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
     surla
    -0.75
     informée
    -0.62
     للاسماء
    -0.56
    WritableDatabase
    -0.54
    脚注の使い方
    -0.54
     Exactos
    -0.53
     houſe
    -0.51
    #+#
    -0.50
    sistor
    -0.50
    CloseOperation
    -0.50
    POSITIVE LOGITS
    rungsseite
    0.43
    Descripció
    0.40
    }],
    0.36
    Marshaller
    0.36
    ])).
    0.36
    %"),
    0.35
    )++;
    0.35
    >--}}
    0.35
     könne
    0.35
    Unmarshaller
    0.34
    Activations Density 1.284%

    No Known Activations