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. 9-GEMMASCOPE-RES-16K
    6. 1516
    Prev
    Next
    INDEX
    Explanations

    terms related to journeys and trips

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    солю
    -0.69
    WarningLevel
    -0.66
    ||}
    -0.66
     Institutes
    -0.65
     femininas
    -0.65
     policía
    -0.64
     disambiguazione
    -0.63
    IFC
    -0.63
     Schrader
    -0.63
    ẠI
    -0.63
    POSITIVE LOGITS
     Journey
    1.43
     journeys
    1.42
     journey
    1.40
    Reise
    1.31
     JOURNEY
    1.31
     trip
    1.30
     trips
    1.25
     Reise
    1.24
    journey
    1.23
    Journey
    1.22
    Activations Density 0.097%

    No Known Activations