© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 3322
    Prev
    Next
    INDEX
    Explanations

    the concept of "free" in various contexts

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

    the word "free" or phrases related to being free/without cost.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 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
     orologio
    -0.49
     Chapitre
    -0.49
     Chapter
    -0.48
    taciones
    -0.47
     novelas
    -0.47
     IndexPath
    -0.47
     Chapters
    -0.47
     postData
    -0.47
    Toponymie
    -0.47
     Pintura
    -0.47
    POSITIVE LOGITS
    Free
    1.24
     Free
    1.20
     free
    1.14
    free
    1.13
     FREE
    1.02
    FREE
    1.01
     frees
    0.85
     Freeport
    0.84
     libre
    0.84
    freed
    0.81
    Activations Density 0.073%

    No Known Activations