© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 13238
    Prev
    Next
    INDEX
    Explanations

    elements related to legal proceedings and testimonies

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

    narrative reversals or changes in story where a person contradicts their previous statement or admission.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    RectangleBorder
    -0.52
     '\\;'
    -0.51
    awtextra
    -0.49
     fitting
    -0.44
    ArrowToggle
    -0.42
     appropriate
    -0.42
    OpenHelper
    -0.40
    apropri
    -0.40
    fitting
    -0.40
     APPROPRI
    -0.40
    POSITIVE LOGITS
     retract
    1.38
     retracted
    1.33
     retraction
    1.22
     reconsider
    1.21
     rescin
    1.09
     reversal
    1.06
     reconsideration
    1.04
     retra
    1.03
     reversed
    1.02
     resc
    1.00
    Activations Density 0.654%

    No Known Activations