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. 14-GEMMASCOPE-RES-16K
    6. 8358
    Prev
    Next
    INDEX
    Explanations

    financial terminology related to corporate performance and market conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_14/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    entingan
    -0.45
     køb
    -0.41
    Advertisement
    -0.41
     retirado
    -0.40
     perhatian
    -0.40
     McCulloch
    -0.40
    featureID
    -0.40
    rawdę
    -0.40
     hábiles
    -0.40
     Berücksich
    -0.40
    POSITIVE LOGITS
    MessageTagHelper
    0.73
    AddTagHelper
    0.51
     cherchés
    0.46
    PYX
    0.45
    MessageOf
    0.45
    IndentedString
    0.44
    utilisons
    0.43
     CanadaChoose
    0.42
    ogast
    0.41
    NameInMap
    0.41
    Activations Density 0.285%

    No Known Activations