© 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. 8619
    Prev
    Next
    INDEX
    Explanations

    phrases related to questioning and quantifying activities

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

    survey questions with temporal or frequency specifications (asking "how long," "how often," "during the past [time period]," 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
    SourceChecksum
    -0.48
     Signalez
    -0.47
     Roskov
    -0.46
    sidemargin
    -0.44
     nahilalakip
    -0.43
     Chwiliwch
    -0.43
    IsMutable
    -0.41
    httphttps
    -0.40
     arşivlendi
    -0.40
     linkovi
    -0.39
    POSITIVE LOGITS
     combien
    1.47
     berapa
    1.42
     cuánto
    1.31
     сколько
    1.29
     cuánt
    1.25
     amount
    1.23
     hoeveel
    1.23
     how
    1.21
     कित
    1.18
     Сколько
    1.17
    Activations Density 0.402%

    No Known Activations