© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 33-GEMMASCOPE-RES-16K
    6. 600
    Prev
    Next
    INDEX
    Explanations

    numerical values and measurements in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/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.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    出版年
    -0.52
     ten
    -0.44
    VersionUID
    -0.37
     оригинала
    -0.37
     nine
    -0.36
    ten
    -0.34
     nueve
    -0.34
    
    -0.33
     eight
    -0.32
    发表于
    -0.32
    POSITIVE LOGITS
    hundred
    1.16
     hundred
    1.15
     hundreds
    1.13
    hundreds
    1.11
    Hundreds
    1.09
     Hundreds
    1.07
     Hundred
    1.06
    Hundred
    1.02
    三百
    1.01
     HUND
    0.99
    Activations Density 1.953%

    No Known Activations