© 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. 9556
    Prev
    Next
    INDEX
    Explanations

    terms related to shared elements or features in various contexts

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

    Preceding words of "release", "cells", "cross", "T", or "base"

    np_acts-logits-general · gemini-2.0-flash

    word pairs forming common phrases

    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
    +#+#
    -0.93
    principalColumn
    -0.91
    EndContext
    -0.86
    httphttps
    -0.85
     increí
    -0.85
    featureID
    -0.81
     avoient
    -0.80
     Beſ
    -0.79
    GOTREF
    -0.79
    alnız
    -0.79
    POSITIVE LOGITS
     
    0.40
     -
    0.35
     blood
    0.34
     review
    0.34
     figure
    0.33
     Main
    0.32
     figures
    0.31
     cubic
    0.31
     L
    0.30
     main
    0.30
    Activations Density 1.074%

    No Known Activations