© 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. 8167
    Prev
    Next
    INDEX
    Explanations

    phrases indicating the presence and significance of specific elements or characteristics within texts

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

    the word "this" used to refer to a specific object or item being discussed.

    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
    ValueStyle
    -0.86
     estekak
    -0.76
     referrerpolicy
    -0.73
    tagHelperRunner
    -0.71
    CppMethod
    -0.70
    fromnode
    -0.65
    ruik
    -0.64
     المعيارى
    -0.64
     protoimpl
    -0.61
    GraphicsUnit
    -0.60
    POSITIVE LOGITS
     témoin
    0.39
     uzn
    0.38
     solchen
    0.35
    gesteld
    0.35
     okre
    0.34
     sprawdz
    0.33
     cherchez
    0.32
    jenige
    0.31
     prawie
    0.31
    もしれません
    0.31
    Activations Density 1.907%

    No Known Activations