© 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. 7604
    Prev
    Next
    INDEX
    Explanations

    connections between visual details and their clarity in various contexts

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

    expressions indicating visual perception or observation (what can be seen or viewed).

    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
     TAMBIÉN
    -0.33
    setLoading
    -0.31
    getRandom
    -0.30
    Unexpected
    -0.29
    ukum
    -0.28
    iro
    -0.28
    上了
    -0.27
    Cuándo
    -0.27
     marad
    -0.27
    itation
    -0.27
    POSITIVE LOGITS
     visible
    1.51
     Visible
    1.32
     clearly
    1.23
    visible
    1.23
     visibility
    1.22
     visibles
    1.22
    clearly
    1.17
     Visibility
    1.15
    Visible
    1.13
     discernible
    1.13
    Activations Density 0.512%

    No Known Activations