© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 35-GEMMASCOPE-RES-16K
    11. 12532
    Prev
    Next
    INDEX
    Explanations

    expressions related to events and their descriptions, particularly focusing on occurrences and significant moments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 35-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_35/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.35.hook_resid_post
    Hook Layer
    35
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    
    -0.56
    帖最后由
    -0.49
    TypedDataSet
    -0.48
    tvguidetime
    -0.45
     Roskov
    -0.40
    parsedMessage
    -0.40
    省市镇
    -0.40
     ब्रेकडाउन
    -0.40
    Filmografie
    -0.37
    лыша
    -0.36
    POSITIVE LOGITS
     day
    3.59
    day
    2.75
     DAY
    2.67
     Day
    2.63
    Day
    2.53
     día
    2.41
    DAY
    2.31
     days
    2.23
     giorno
    2.11
     journée
    2.02
    Activations Density 1.067%

    No Known Activations