© 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. 10441
    Prev
    Next
    INDEX
    Explanations

    objects and items related to daily life and experiences

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

    specific objects and things found in everyday life (food, clothing, vehicles, tools, etc.).

    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
    Rüyada
    -0.64
    intios
    -0.59
     referrerpolicy
    -0.58
    oa̍t
    -0.56
    Diweddarwch
    -0.56
    AddTagHelper
    -0.54
     initComponents
    -0.53
    GOTREF
    -0.52
    felves
    -0.52
    ๬
    -0.52
    POSITIVE LOGITS
     headphones
    0.35
     bowels
    0.35
     turísticos
    0.34
     espirituales
    0.34
     microondas
    0.33
     tubes
    0.33
     téléph
    0.32
    airplane
    0.32
     microphone
    0.32
     mentales
    0.31
    Activations Density 0.603%

    No Known Activations