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. 13-GEMMASCOPE-RES-16K
    6. 11649
    Prev
    Next
    INDEX
    Explanations

    the word "keep" and its variations, indicating a focus on persistence or maintaining something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    
    -1.04
    OGND
    -0.82
    ValueStyle
    -0.82
    Personensuche
    -0.77
     Adamson
    -0.75
    Portale
    -0.73
    digm
    -0.70
    posedge
    -0.69
     Lang
    -0.68
     Dorsey
    -0.68
    POSITIVE LOGITS
     keep
    1.56
    KEEP
    1.51
    Keeps
    1.51
     KEEP
    1.50
    keep
    1.48
     kept
    1.48
     Keep
    1.42
     keeps
    1.40
    Keep
    1.38
     Keeping
    1.36
    Activations Density 0.033%

    No Known Activations