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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 19-GEMMASCOPE-RES-16K
    6. 15750
    Prev
    Next
    INDEX
    Explanations

    references to medical and scientific organizations and institutions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    randrange
    -0.45
    щество
    -0.43
     esternos
    -0.42
    وصلات
    -0.42
    Schedulers
    -0.40
     término
    -0.40
     leva
    -0.38
    amata
    -0.38
     concentrated
    -0.38
     considered
    -0.38
    POSITIVE LOGITS
    #+#
    0.86
     nakalista
    0.73
     Paglinawan
    0.70
    OrNil
    0.70
    migrationBuilder
    0.67
    发表于
    0.66
    LookAnd
    0.65
     lenker
    0.64
    الإنجليزية
    0.63
    jspx
    0.62
    Activations Density 0.452%

    No Known Activations