© 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. 0-GEMMASCOPE-RES-16K
    11. 717
    Prev
    Next
    INDEX
    Explanations

    variations of the prefix "Pro" relating to professional or procedural contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_0/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    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
    -0.45
    sidemargin
    -0.42
     تعدى
    -0.40
     дописавши
    -0.40
    InjectAttribute
    -0.38
     насељу
    -0.37
     CascadeType
    -0.34
    ležit
    -0.34
     Itália
    -0.33
    glą
    -0.32
    POSITIVE LOGITS
     Pro
    2.70
    Pro
    2.69
     PRO
    2.55
    PRO
    2.50
    pro
    2.42
     pro
    2.23
     Про
    2.13
    Про
    2.05
     Proctor
    2.02
    プロ
    1.98
    Activations Density 0.233%

    No Known Activations