Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 20-GEMMASCOPE-RES-131K
    6. 73713
    Prev
    Next
    INDEX
    Explanations

    the word "until" and its variations, indicating a focus on time or conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    esse
    -0.46
    piac
    -0.42
    er
    -0.42
     noires
    -0.41
    cis
    -0.41
     opinion
    -0.40
     peuples
    -0.40
    itects
    -0.40
     actes
    -0.40
     verres
    -0.40
    POSITIVE LOGITS
     until
    1.03
    until
    1.02
     Until
    1.00
    Until
    0.99
     untill
    0.92
     UNTIL
    0.91
     SwitchCompat
    0.81
     يتيمه
    0.79
     Till
    0.75
    waitUntil
    0.75
    Activations Density 0.020%

    No Known Activations