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. 2649
    Prev
    Next
    INDEX
    Explanations

    expressions of belief and conviction

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

    "believe" or "believed"

    np_acts-logits-general · gemini-2.0-flash

    believe me

    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
     оригіналу
    -0.71
    gdx
    -0.70
    TagHelpers
    -0.69
     kaynağından
    -0.65
    ContentAsync
    -0.64
    ="">
    
    -0.64
    XmlAccessorType
    -0.62
    displayquote
    -0.60
    SourceChecksum
    -0.60
    atimes
    -0.59
    POSITIVE LOGITS
     BELIEVE
    1.01
     believe
    0.98
     strongly
    0.96
    believe
    0.95
    Believe
    0.93
     Believe
    0.92
     believes
    0.91
     myſelf
    0.85
     Beliefs
    0.84
     croy
    0.83
    Activations Density 0.071%

    No Known Activations