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. 5-GEMMASCOPE-RES-16K
    6. 9054
    Prev
    Next
    INDEX
    Explanations

    references to time-related concepts, particularly the word "last" and its derivatives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     plainte
    -0.84
     grossesse
    -0.72
     épis
    -0.71
    uguetes
    -0.68
     deoarece
    -0.68
     faptul
    -0.67
     expéri
    -0.67
     pleinement
    -0.66
     gravidanza
    -0.65
     vektör
    -0.65
    POSITIVE LOGITS
    last
    0.76
    uxxxx
    0.75
     last
    0.74
     LAST
    0.72
    GraphicsUnit
    0.69
     незавершена
    0.69
    lastTime
    0.68
    AsUp
    0.68
     CURLOPT
    0.65
     برانيه
    0.65
    Activations Density 0.046%

    No Known Activations