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. 0-GEMMASCOPE-RES-16K
    6. 6642
    Prev
    Next
    INDEX
    Explanations

    adjectives and adverbs that evoke strong emotional or descriptive responses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Gen
    -0.49
     Läng
    -0.48
     recto
    -0.48
    ofag
    -0.47
     Alc
    -0.46
     hæ
    -0.46
     væ
    -0.46
     loue
    -0.46
     timbre
    -0.44
     Española
    -0.44
    POSITIVE LOGITS
    ingly
    1.06
    /*
    0.90
    tably
    0.90
    PerformLayout
    0.90
    ously
    0.87
    matically
    0.84
    ishly
    0.83
    vely
    0.83
    sively
    0.79
    ally
    0.78
    Activations Density 2.268%

    No Known Activations