© 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. 20-GEMMASCOPE-RES-16K
    6. 10604
    Prev
    Next
    INDEX
    Explanations

    code-related constructs specifically involving data structures and function declarations

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

    Code or special characters

    np_acts-logits-general · gemini-2.0-flash

    pointer member access

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    !
    -0.51
    isSuccessful
    -0.48
    然
    -0.46
    IBOutlet
    -0.44
    ExecuteNonQuery
    -0.44
    !,
    -0.44
     diserta
    -0.43
    RunAsync
    -0.42
    !!!
    -0.42
    MethodManager
    -0.42
    POSITIVE LOGITS
    Portail
    0.87
     Roskov
    0.69
    actéristique
    0.63
     تضيفلها
    0.61
    AccessorTable
    0.59
    Datuak
    0.59
    بوابة
    0.57
    ValueStyle
    0.57
     TAMBÉM
    0.55
     pinulongan
    0.55
    Activations Density 0.388%

    No Known Activations