© 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. 8175
    Prev
    Next
    INDEX
    Explanations

    error handling constructs and exception-related statements in programming code

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

    Python exception handling

    np_acts-logits-general · gemini-2.0-flash

    handling exceptions and errors

    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
    賀状
    -0.44
    vs
    -0.42
     præ
    -0.39
    {{{
    -0.39
     Between
    -0.39
     lanterna
    -0.39
     izle
    -0.38
    烂
    -0.37
    ti
    -0.37
    Between
    -0.37
    POSITIVE LOGITS
    tagHelperRunner
    0.81
    InitVars
    0.77
    .}}
    0.76
    hyrchwyd
    0.69
     Biôgrafia
    0.69
    Aktualisiert
    0.68
    kloped
    0.68
     WaitForSeconds
    0.68
     незавершена
    0.67
     Standard
    0.67
    Activations Density 0.115%

    No Known Activations