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. 20-GEMMASCOPE-RES-16K
    6. 4107
    Prev
    Next
    INDEX
    Explanations

    references to speeches and presentations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    speeches or addresses

    np_acts-logits-general · gemini-2.0-flash

    public address or speech

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    సు
    -0.70
     CreateTagHelper
    -0.68
     متعلقه
    -0.63
     Metacritic
    -0.57
    ետ
    -0.57
    UnitTesting
    -0.57
    DataAnnotations
    -0.54
     découverte
    -0.53
    racene
    -0.51
    ništ
    -0.51
    POSITIVE LOGITS
     speech
    2.07
     speeches
    1.90
     Speech
    1.67
    speech
    1.65
     Speeches
    1.51
    Speech
    1.50
     SPEECH
    1.48
     speaking
    1.46
     speaker
    1.46
     address
    1.46
    Activations Density 0.347%

    No Known Activations