© 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. 83128
    Prev
    Next
    INDEX
    Explanations

    descriptions of visually impactful or notable features

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

    striking observations

    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
    hyrchwyd
    -0.69
     Roskov
    -0.58
     дописавши
    -0.57
     HasFactory
    -0.56
     noDo
    -0.56
    GeoNames
    -0.52
    BASEPATH
    -0.52
    цездатний
    -0.51
     NavController
    -0.51
     FormBuilder
    -0.51
    POSITIVE LOGITS
     striking
    1.92
     Striking
    1.61
     strikingly
    1.25
     remarkable
    1.08
     stunning
    1.04
    stunning
    1.04
     startling
    0.93
    Stunning
    0.91
     impressive
    0.88
     astonishing
    0.86
    Activations Density 0.004%

    No Known Activations