© 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. 22-GEMMASCOPE-RES-16K
    11. 8188
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and symbols

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

    Tokens followed by abbreviations

    np_acts-logits-general · gemini-2.0-flash

    N followed by abbreviations/names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ThroughAttribute
    -0.52
     صوتيه
    -0.49
     autorytatywna
    -0.48
    tagext
    -0.44
     Drapeau
    -0.44
    UserScript
    -0.43
    
    -0.43
     GoogleFonts
    -0.42
     itſelf
    -0.42
     Amethyst
    -0.42
    POSITIVE LOGITS
     NP
    1.09
     NM
    1.08
     NR
    1.07
     NU
    1.07
     Nicholas
    1.05
     NC
    1.05
     NS
    1.05
     Nelson
    1.04
     NF
    1.04
     Nicolas
    1.03
    Activations Density 2.062%

    No Known Activations