© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 23-GEMMASCOPE-RES-16K
    11. 4566
    Prev
    Next
    INDEX
    Explanations

    quantitative comparisons and measurements related to populations or groups

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    BeginContext
    -0.55
     betweenstory
    -0.54
    ENSE
    -0.51
    EDEFAULT
    -0.50
     createContext
    -0.49
     CURIAM
    -0.49
     pymongo
    -0.47
    rspec
    -0.47
    IContainer
    -0.45
    checkNotNull
    -0.45
    POSITIVE LOGITS
     half
    4.11
    half
    3.60
    Half
    3.44
     Half
    3.39
     HALF
    3.13
    HALF
    2.83
     halves
    2.53
     halv
    2.47
     setengah
    2.42
     metade
    2.33
    Activations Density 0.435%

    No Known Activations