Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 25-GEMMASCOPE-RES-16K
    6. 5775
    Prev
    Next
    INDEX
    Explanations

    conversations about social and political movements, especially regarding reform and agreements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     AssemblyCulture
    -0.58
    batik
    -0.50
    liferay
    -0.46
    prepareStatement
    -0.46
     nici
    -0.46
     erb
    -0.45
    TagHelper
    -0.45
     חיצוניים
    -0.44
    сылкі
    -0.43
     shayari
    -0.43
    POSITIVE LOGITS
     picking
    1.21
     pick
    1.18
     picked
    1.17
     picks
    1.13
     PICK
    1.05
     Picking
    1.05
     Pick
    1.04
    Pick
    1.01
    picking
    1.00
    pick
    0.99
    Activations Density 0.402%

    No Known Activations