© 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. 18-GEMMASCOPE-RES-16K
    11. 8443
    Prev
    Next
    INDEX
    Explanations

    keywords related to data structures and object-oriented programming in code

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

    after capitalized words

    np_acts-logits-general · gemini-2.0-flash

    "new" or "bar" followed by "("

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     @"/
    -0.81
     net
    -0.63
    IUrlHelper
    -0.61
     ExecuteAsync
    -0.59
    
    -0.59
    __).
    -0.57
     "..\..\
    -0.56
    HideFlags
    -0.55
    __["
    -0.55
    cred
    -0.54
    POSITIVE LOGITS
    Hochspringen
    0.57
     GDR
    0.49
    JoinTable
    0.48
     Sochi
    0.48
     Merced
    0.48
    inigungs
    0.47
     externes
    0.47
     TextStyle
    0.46
     LEYENDO
    0.46
    зулта
    0.46
    Activations Density 0.061%

    No Known Activations