© 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. 35-GEMMASCOPE-RES-16K
    6. 13755
    Prev
    Next
    INDEX
    Explanations

    concepts related to evidence, conviction, and the implications of proof in legal contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 35-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_35/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.35.hook_resid_post
    Hook Layer
    35
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    pip
    -0.36
    togram
    -0.35
    UserScript
    -0.35
    </caption>
    -0.34
    сар
    -0.33
    IsContent
    -0.33
    ariConfig
    -0.33
    rsiniz
    -0.32
    ArgsConstructor
    -0.32
    AutoModerator
    -0.32
    POSITIVE LOGITS
     beyond
    3.80
    beyond
    3.45
     Beyond
    3.22
    Beyond
    3.16
     BEYOND
    2.97
    YOND
    2.02
     além
    1.98
    delà
    1.89
     oltre
    1.76
     delà
    1.59
    Activations Density 1.239%

    No Known Activations