© 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
    7. Residual Stream - 16k
    9. 31-GEMMASCOPE-RES-16K
    11. 14308
    Prev
    Next
    INDEX
    Explanations

    experimental details and results related to behavioral and physiological studies in controlled environments

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

    scientific methodology and experimental procedures in research papers.

    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
    GEBURTSDATUM
    -0.63
    ChildScrollView
    -0.57
    ckså
    -0.57
    AISSEE
    -0.50
    EDEFAULT
    -0.48
     AssemblyCulture
    -0.47
    hosted
    -0.46
    </tfoot>
    -0.46
    Portail
    -0.46
    awtextra
    -0.45
    POSITIVE LOGITS
     treatment
    1.41
     treatments
    1.39
     Treatments
    1.21
     Treatment
    1.20
     experimental
    1.11
    treatment
    1.11
    Treatment
    1.10
    Treatments
    1.09
     TREATMENT
    1.05
     treated
    1.01
    Activations Density 2.067%

    No Known Activations