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. 3224
    Prev
    Next
    INDEX
    Explanations

    terms associated with the concept of "freedom" or "being free."

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

    Tokens after "Free" or "free"

    np_acts-logits-general · gemini-2.0-flash

    free something

    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
    AndEndTag
    -0.87
    OGND
    -0.85
     CreateTagHelper
    -0.78
    enumi
    -0.76
    rungsseite
    -0.73
    StoryboardSegue
    -0.72
     Италијани
    -0.72
     himo
    -0.71
    Collegamenti
    -0.69
     distanciation
    -0.67
    POSITIVE LOGITS
     Free
    1.01
    bies
    0.91
     free
    0.86
    bie
    0.84
    Free
    0.83
    FREE
    0.81
     FREE
    0.77
    🆓
    0.74
     libre
    0.72
    free
    0.72
    Activations Density 0.113%

    No Known Activations