© 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. 10293
    Prev
    Next
    INDEX
    Explanations

    mentions of individuals, particularly those in notable positions or roles

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

    Attribution phrases (said, says, stated)

    np_acts-logits-general · gemini-2.0-flash

    reporting speech or quotes

    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
     EconPapers
    -0.95
     ModelExpression
    -0.68
     kasarigan
    -0.65
     '\\;'
    -0.62
     AssemblyCulture
    -0.60
    verwijspagina
    -0.58
     beginnetje
    -0.57
     nahilalakip
    -0.57
     насељу
    -0.56
    BeginContext
    -0.54
    POSITIVE LOGITS
     refiri
    1.03
     referring
    1.01
     parlando
    0.71
     referencing
    0.70
     quoting
    0.69
     jokingly
    0.65
    .
    0.65
     citing
    0.64
     henvis
    0.63
     noting
    0.63
    Activations Density 0.116%

    No Known Activations