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. 12293
    Prev
    Next
    INDEX
    Explanations

    terms related to employee gamification and rewards

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

    Strings of text with msgstr ""

    np_acts-logits-general · gemini-2.0-flash

    ir. model or ui references

    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
    рите
    -0.55
     Alberta
    -0.52
     Dol
    -0.47
    Alberta
    -0.47
     reclamation
    -0.44
    θα
    -0.43
    laq
    -0.43
    اريخ
    -0.43
     getItemCount
    -0.43
     Baja
    -0.43
    POSITIVE LOGITS
     يتيمه
    0.98
    AndEndTag
    0.94
    IndentedString
    0.85
     للاسماء
    0.84
     Normdatei
    0.71
    RetentionPolicy
    0.71
    Autoritní
    0.70
    цездатний
    0.69
     ivelany
    0.68
     مرئيه
    0.68
    Activations Density 0.103%

    No Known Activations