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. 16-GEMMASCOPE-RES-16K
    6. 12844
    Prev
    Next
    INDEX
    Explanations

    constructs related to specific rates or records, particularly in the context of formal agreements or evaluations

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

    Prepositions: of, from, the, after, for

    np_acts-logits-general · gemini-2.0-flash

    preposition followed by specific noun

    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
    rungsseite
    -1.18
    Personendaten
    -1.08
     '\\;'
    -1.02
     Roskov
    -1.01
    SharedDtor
    -1.01
    writeFieldEnd
    -0.96
    SequentialGroup
    -0.90
     Paglinawan
    -0.89
     Baillargeon
    -0.89
    SourceChecksum
    -0.89
    POSITIVE LOGITS
      
    0.52
    <eos>
    0.49
    ↵↵↵
    0.46
    .
    0.44
    ...
    0.44
    …
    0.44
     hôm
    0.44
     concent
    0.43
     also
    0.42
    ↵↵
    0.42
    Activations Density 0.602%

    No Known Activations