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. 16-GEMMASCOPE-RES-16K
    6. 3063
    Prev
    Next
    INDEX
    Explanations

    conditional statements and obligations

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

    before verbs like "take," "make," "recover."

    np_acts-logits-general · gemini-2.0-flash

    to say, to take, not break

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     الع
    -0.40
     pertanto
    -0.39
    Mé
    -0.38
    ino
    -0.38
     substantially
    -0.37
    চ্
    -0.37
     særlig
    -0.36
     mourut
    -0.36
     comprises
    -0.36
    Boy
    -0.36
    POSITIVE LOGITS
    MessageTagHelper
    0.96
     ModelExpression
    0.93
    parsedMessage
    0.93
    Rüyada
    0.92
    tvguidetime
    0.91
     виправивши
    0.89
    findpost
    0.87
    IUrlHelper
    0.87
    InputTagHelper
    0.87
     HttpNotFound
    0.85
    Activations Density 0.395%

    No Known Activations