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. 22-GEMMASCOPE-RES-16K
    6. 3428
    Prev
    Next
    INDEX
    Explanations

    punctuations and phrases that indicate quotations or citations in legal contexts

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

    Punctuation followed by transition words

    np_acts-logits-general · gemini-2.0-flash

    contrast, concession, or cause/effect

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     فريبيس
    -0.74
     otomatig
    -0.67
    MigrationBuilder
    -0.63
    :]:
    -0.55
    []>(
    -0.55
     насељу
    -0.53
    PreferredItem
    -0.52
     pero
    -0.50
    是自己
    -0.49
    thenReturn
    -0.48
    POSITIVE LOGITS
     unlike
    1.06
     although
    1.01
     given
    0.96
     despite
    0.96
     while
    0.95
    unlike
    0.93
     contrary
    0.91
     aside
    0.87
     since
    0.86
     notwithstanding
    0.85
    Activations Density 0.138%

    No Known Activations