© 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. 6746
    Prev
    Next
    INDEX
    Explanations

    phrases highlighting the impact of individual actions or contributions

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

    phrases expressing the impact or importance of someone's actions or efforts on others.

    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
    Попис
    -0.50
     CreateTagHelper
    -0.41
     intéressante
    -0.40
    lorette
    -0.38
    alogy
    -0.38
    şört
    -0.38
     regalías
    -0.34
    alties
    -0.34
    afficheront
    -0.34
    BeginContext
    -0.34
    POSITIVE LOGITS
     difference
    1.52
    difference
    1.38
     Difference
    1.22
    Difference
    1.21
     DIFFERENCE
    1.19
     différence
    1.02
     impact
    1.00
     diferença
    0.98
     diferencia
    0.98
     verschil
    0.94
    Activations Density 0.121%

    No Known Activations