© 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. 3356
    Prev
    Next
    INDEX
    Explanations

    elements related to programming structures, functions, and errors

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

    Tokens after a capitalized letter

    np_acts-logits-general · gemini-2.0-flash

    current process, error codes, file access

    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
    ercises
    -0.78
    FTFY
    -0.76
    ecutive
    -0.75
    UALA
    -0.70
    ratulations
    -0.69
    hematical
    -0.66
    eſ
    -0.64
    ftance
    -0.64
    couvrez
    -0.63
     дописавши
    -0.62
    POSITIVE LOGITS
    enderror
    0.64
    >//
    0.64
    res
    0.58
    fml
    0.58
     initComponents
    0.57
    se
    0.57
    inf
    0.57
    any
    0.57
    bt
    0.56
    select
    0.55
    Activations Density 0.628%

    No Known Activations