© 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 - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 9417
    Prev
    Next
    INDEX
    Explanations

    references to specific types of organisms or taxa, particularly those denoted as pseudo or pro

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

    "pseudo" or "proto."

    np_acts-logits-general · gemini-2.0-flash

    pseudo and quasi prefixes

    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-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
     propOrder
    -0.46
    ValueGeneration
    -0.45
     Wikiseite
    -0.44
    ButtonModule
    -0.42
    featureID
    -0.42
    EndContext
    -0.41
     pinulongan
    -0.40
     Inscrivez
    -0.40
    RTLR
    -0.39
     Verhältnis
    -0.39
    POSITIVE LOGITS
     pseudo
    0.74
     Pseudo
    0.72
    pseudo
    0.70
    Pseudo
    0.68
     Quasi
    0.65
    Quasi
    0.63
    quasi
    0.63
     quasi
    0.61
     fake
    0.61
     Fake
    0.60
    Activations Density 1.620%

    No Known Activations