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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 5-GEMMASCOPE-RES-16K
    11. 383
    Prev
    Next
    INDEX
    Explanations

    the prefix "Pro" or related terms indicating professional or proactive aspects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Magnetism
    -1.00
    èlement
    -0.87
     BIBSYS
    -0.87
    Diwedd
    -0.86
     HasFactory
    -0.84
     Melch
    -0.84
     Theſe
    -0.84
    Примітки
    -0.81
     encu
    -0.80
     Montagu
    -0.79
    POSITIVE LOGITS
    Pro
    2.46
     Pro
    2.46
    pro
    2.22
     pro
    2.20
     PRO
    2.15
    PRO
    2.01
    プロ
    1.49
     Pros
    1.45
     pros
    1.40
    Про
    1.36
    Activations Density 0.057%

    No Known Activations