© 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. 3990
    Prev
    Next
    INDEX
    Explanations

    highly technical identifiers and variable names in programming code

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

    Single-character tokens

    np_acts-logits-general · gemini-2.0-flash

    abbreviations followed by suffixes

    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
    .,
    -0.55
    abases
    -0.51
    Pyx
    -0.48
     isSet
    -0.48
    gameserver
    -0.47
    parral
    -0.45
    …
    -0.45
     fla
    -0.45
     azar
    -0.44
    ichthys
    -0.44
    POSITIVE LOGITS
     виправивши
    0.83
    Personendaten
    0.69
     للاسماء
    0.67
    曖昧さ回避
    0.66
     Baillargeon
    0.66
     kaarangay
    0.66
     Gregorian
    0.63
     Elisha
    0.62
     ErrIntOverflow
    0.61
    =$?
    0.61
    Activations Density 0.955%

    No Known Activations