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

    Neuronpedia

    APICircuit 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. 21-GEMMASCOPE-RES-16K
    6. 6466
    Prev
    Next
    INDEX
    Explanations

    instances of the verb "is" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    хьтан
    -0.83
    MigrationBuilder
    -0.79
     Normdatei
    -0.72
     linkovi
    -0.70
    География
    -0.68
    MLLoader
    -0.68
    fhir
    -0.68
    LEncoder
    -0.66
    IsMutable
    -0.66
     ddelweddau
    -0.65
    POSITIVE LOGITS
     important
    0.87
     clear
    0.74
     true
    0.72
     hoped
    0.71
     through
    0.66
     crucial
    0.64
     imperative
    0.64
     common
    0.64
     unclear
    0.63
     impossible
    0.63
    Activations Density 0.169%

    No Known Activations