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. 11942
    Prev
    Next
    INDEX
    Explanations

    phrases or statements related to the actions or comments of individuals in a narrative context, particularly focusing on references to people and events in relation to major themes or discussions

    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
    enumii
    -0.63
    ętr
    -0.60
    клопе
    -0.59
    ).
    
    -0.58
     CreateTagHelper
    -0.58
     .
    
    -0.57
    ]--;
    -0.57
    audiovisuel
    -0.56
    ritation
    -0.56
     :
    
    -0.56
    POSITIVE LOGITS
     [
    0.83
    +#+#
    0.72
    ագրություններ
    0.59
     [$
    0.58
    ,”
    0.56
    ,"
    0.56
     my
    0.51
     minha
    0.51
     [_
    0.50
     setuptools
    0.49
    Activations Density 0.211%

    No Known Activations