© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 2-GEMMASCOPE-RES-16K
    11. 6416
    Prev
    Next
    INDEX
    Explanations

    instances of the word "pro," particularly in the context of professional or proactive concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/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.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    期刊论文
    -0.43
     Hoek
    -0.42
    念
    -0.39
     CreateTagHelper
    -0.36
    <bos>
    -0.36
    êques
    -0.36
    razos
    -0.35
    MessageId
    -0.35
    ologiques
    -0.35
     pronunci
    -0.35
    POSITIVE LOGITS
     Pro
    3.59
     pro
    3.41
    Pro
    3.27
    pro
    3.05
    PRO
    2.23
     PRO
    2.22
    プロ
    1.70
    epro
    1.34
     pros
    1.32
     про
    1.30
    Activations Density 0.258%

    No Known Activations