© 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-2-2B
    4. Residual Stream - 16k
    5. 22-GEMMASCOPE-RES-16K
    6. 13287
    Prev
    Next
    INDEX
    Explanations

    references to programming concepts, particularly around handling variables and functions in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
     insuffisamment
    -0.61
    новниш
    -0.56
    SPJ
    -0.52
    protoimpl
    -0.52
    horabuena
    -0.50
    Readings
    -0.50
    AccessException
    -0.50
    ctomy
    -0.49
    styleType
    -0.48
     devront
    -0.48
    POSITIVE LOGITS
     complic
    0.61
     😂
    0.60
     fucked
    0.59
    SEGUIR
    0.59
     EClass
    0.59
     bullshit
    0.58
     blz
    0.57
     cutest
    0.57
     stras
    0.56
     xD
    0.56
    Activations Density 0.062%

    No Known Activations