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-2-9B
    4. Residual Stream - 16k
    5. 15-GEMMASCOPE-RES-16K
    6. 1884
    Prev
    Next
    INDEX
    Explanations

    qualities related to positive and warm emotional attributes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_15/width_16k/average_l0_131
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    IntoConstraints
    -0.57
     препратки
    -0.57
     estekak
    -0.56
    CppMethod
    -0.56
    Välislingid
    -0.51
    hyrchwyd
    -0.50
    ConstraintMaker
    -0.50
    homonymie
    -0.49
     excel
    -0.49
    FromArgb
    -0.48
    POSITIVE LOGITS
     and
    0.50
     &
    0.40
     coloré
    0.38
     civilización
    0.37
     abundancia
    0.37
     Persön
    0.36
     solidaridad
    0.36
     corrupción
    0.36
     duradero
    0.35
    setLayoutManager
    0.35
    Activations Density 0.608%

    No Known Activations