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-2-9B
    4. Residual Stream - 131k
    5. 24-GEMMASCOPE-RES-131K
    6. 751
    Prev
    Next
    INDEX
    Explanations

    references to specific days related to significant events

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

    day before or day of events

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_131k/average_l0_97
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     hjælp
    -0.38
     obdob
    -0.35
    nál
    -0.35
     toiminta
    -0.35
    ruimte
    -0.35
     místa
    -0.34
     rapides
    -0.34
     space
    -0.34
     continuing
    -0.33
     plads
    -0.33
    POSITIVE LOGITS
     day
    0.94
     DAY
    0.84
     Day
    0.80
     día
    0.79
    principalColumn
    0.79
    Day
    0.78
    DAY
    0.73
    day
    0.73
     giorno
    0.73
     незавершена
    0.72
    Activations Density 0.027%

    No Known Activations