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. 11-GEMMASCOPE-RES-16K
    6. 5970
    Prev
    Next
    INDEX
    Explanations

    sentences related to criticism and disagreement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     resourceCulture
    -0.67
    tagHelper
    -0.62
    <thead>
    -0.56
    XmlSchema
    -0.54
    PROTOBUF
    -0.53
    PYX
    -0.51
    uxxxx
    -0.50
    ,:);
    -0.50
    rawDesc
    -0.49
     IERC
    -0.48
    POSITIVE LOGITS
     réactions
    0.71
     Reaktion
    0.67
     response
    0.66
     reação
    0.65
     responded
    0.64
     rebuttal
    0.64
     reacción
    0.63
     réaction
    0.62
     reacciones
    0.61
     RESPONSE
    0.61
    Activations Density 0.546%

    No Known Activations