© 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. 9-GEMMASCOPE-RES-16K
    6. 9149
    Prev
    Next
    INDEX
    Explanations

    terms related to sensitivity and detection methods

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

    words related to sensitivity, particularly when describing physical instruments, methods, areas of the body, or responses to stimuli.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_9/width_16k/average_l0_100
    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
     vôtre
    -0.48
     MainAxisSize
    -0.46
     armée
    -0.46
     réus
    -0.46
     nôtre
    -0.43
     totalité
    -0.41
     koul
    -0.41
     debout
    -0.40
     anaknya
    -0.40
     diversión
    -0.39
    POSITIVE LOGITS
     sensitive
    2.17
     Sensitive
    2.03
     sensitivity
    2.03
    Sensitive
    1.96
    sensitive
    1.92
     Sensitivity
    1.91
    Sensitivity
    1.80
    sensitivity
    1.80
     sensitivities
    1.69
     sensi
    1.68
    Activations Density 0.229%

    No Known Activations