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. 5-GEMMASCOPE-RES-16K
    6. 14620
    Prev
    Next
    INDEX
    Explanations

    phrases that convey a sense of freedom or the invitation to act without restrictions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ējās
    -0.61
    XmlEnum
    -0.60
    ایج
    -0.58
     realises
    -0.58
     realising
    -0.57
     realised
    -0.56
     članak
    -0.55
    yeezy
    -0.55
     Siamese
    -0.53
    VideoView
    -0.53
    POSITIVE LOGITS
     free
    0.82
     freely
    0.80
    StoryboardSegue
    0.72
     Free
    0.71
    verständlich
    0.68
     bebas
    0.66
    free
    0.66
     FREE
    0.65
    Free
    0.65
     Chwiliwch
    0.64
    Activations Density 0.049%

    No Known Activations