Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 16-GEMMASCOPE-RES-16K
    6. 1403
    Prev
    Next
    INDEX
    Explanations

    conditional statements and filtering criteria in programming contexts

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

    SQL "WHERE" and "FILTER" clauses

    np_acts-logits-general · gemini-2.0-flash

    conditional filter

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     _("
    -0.52
     تضيفلها
    -0.51
     utafitiHapana
    -0.50
     gourd
    -0.48
    bewerken
    -0.47
     tartalomajánló
    -0.46
    bodyParser
    -0.45
    AxisSize
    -0.45
    ברס
    -0.45
     $[-
    -0.44
    POSITIVE LOGITS
     !(
    0.70
     !
    0.68
    IsContent
    0.65
     presence
    0.62
     (!
    0.59
    TRUE
    0.58
     circonstances
    0.57
     présence
    0.55
    UnitTesting
    0.55
    (!(
    0.54
    Activations Density 0.547%

    No Known Activations