© 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. 35705
    Prev
    Next
    INDEX
    Explanations

    technical terminology and specifications related to molecular properties, including weight and affinity

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

    high quality or intensity

    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
    expandindo
    -0.49
     utafitiHapana
    -0.48
     pensieri
    -0.44
    RTLI
    -0.41
     Administrativna
    -0.39
    Scénario
    -0.38
    AnimationsModule
    -0.37
     Autorisations
    -0.37
    🇶
    -0.35
     parseFrom
    -0.34
    POSITIVE LOGITS
    高质量
    0.60
     hochwer
    0.52
     newOwner
    0.49
     hochwertige
    0.48
    irited
    0.48
    优质
    0.45
     multiuso
    0.45
    High
    0.45
     насељу
    0.44
    Kaynakça
    0.44
    Activations Density 0.107%

    No Known Activations