© 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. 13719
    Prev
    Next
    INDEX
    Explanations

    questions and contemplative themes regarding knowledge and understanding

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

    poetic or literary language with emotional and introspective themes.

    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
    httphttps
    -0.66
    NameInMap
    -0.64
    apimachinery
    -0.63
    styleType
    -0.58
    WithIOException
    -0.55
     getItemId
    -0.54
    +#+
    -0.52
    NamedQuery
    -0.52
    setVerticalGroup
    -0.51
    wpi
    -0.51
    POSITIVE LOGITS
    ględ
    0.36
     conmigo
    0.34
     Gefühl
    0.33
    蚪
    0.30
     Архів
    0.30
    ช
    0.30
    VNB
    0.30
    CrossRef
    0.30
    டை
    0.29
     rağmen
    0.29
    Activations Density 0.106%

    No Known Activations