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. 22-GEMMASCOPE-RES-16K
    6. 5950
    Prev
    Next
    INDEX
    Explanations

    PHP functions and commands related to output and data rendering

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

    Followed by a quotation mark or dollar sign

    np_acts-logits-general · gemini-2.0-flash

    programming output

    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
    principalColumn
    -1.29
     betweenstory
    -1.06
     Normdatei
    -1.05
    Билгалдахарш
    -1.00
    ViewImports
    -0.99
     <=",
    -0.92
     Baillargeon
    -0.92
     nakalista
    -0.91
    LLocation
    -0.91
     الحره
    -0.89
    POSITIVE LOGITS
    (
    0.67
     $
    0.56
     "
    0.54
    "
    0.51
    žia
    0.46
     producer
    0.43
     '
    0.43
     
    0.43
     <<
    0.43
     ”
    0.42
    Activations Density 0.040%

    No Known Activations