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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 17-GEMMASCOPE-RES-16K
    6. 6389
    Prev
    Next
    INDEX
    Explanations

    instances where the concept of time is expressed or emphasized

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    MigrationBuilder
    -0.92
     ModelExpression
    -0.88
     autorytatywna
    -0.83
     saites
    -0.80
     CWE
    -0.80
    __':
    
    -0.77
    SOUNDBITE
    -0.76
     Walkover
    -0.72
     <<<<<<<<<<<<<<
    -0.71
     esternos
    -0.71
    POSITIVE LOGITS
     to
    0.67
     for
    0.61
     action
    0.59
     step
    0.56
     take
    0.53
     started
    0.52
     start
    0.51
     actie
    0.51
     real
    0.51
    そろそろ
    0.50
    Activations Density 0.077%

    No Known Activations