© 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. 11626
    Prev
    Next
    INDEX
    Explanations

    references to a specific name or term ("Ver")

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

    words starting with Ver or Ser

    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
     المعيارى
    -0.74
    /**
    -0.65
    parsedMessage
    -0.65
    tagHelperRunner
    -0.64
     Monfieur
    -0.62
    ahul
    -0.61
    WithIOException
    -0.60
     Adamson
    -0.58
    bootstrapcdn
    -0.58
    bleau
    -0.58
    POSITIVE LOGITS
     Ver
    1.77
    Ver
    1.52
     VER
    1.02
     Вер
    0.82
    Vertices
    0.74
     Verm
    0.71
    ver
    0.66
    VER
    0.62
     Vertigo
    0.59
    Вер
    0.58
    Activations Density 0.007%

    No Known Activations