© 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. 12512
    Prev
    Next
    INDEX
    Explanations

    quantities of "few" in different contexts

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

    expressions indicating a small quantity of time or distance (e.g., "a few days," "a few months," "a few hundred metres").

    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
     lenker
    -0.46
     some
    -0.43
     fome
    -0.33
     rac
    -0.32
    some
    -0.31
    MENAFN
    -0.31
    BrowserModule
    -0.31
    InstanceState
    -0.30
     Esch
    -0.30
    ταν
    -0.30
    POSITIVE LOGITS
     dozen
    1.02
     hundred
    0.95
     wenige
    0.91
     thousand
    0.83
     weeks
    0.82
     hundert
    0.79
     wenigen
    0.78
    hundred
    0.78
    dozen
    0.77
     tausend
    0.75
    Activations Density 0.114%

    No Known Activations