Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 18-GEMMASCOPE-RES-16K
    6. 1024
    Prev
    Next
    INDEX
    Explanations

    content related to warranties and guarantees

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

    guarantees or warranties

    np_acts-logits-general · gemini-2.0-flash

    warranty and guarantee

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     broth
    -0.55
    withIdentifier
    -0.47
     block
    -0.46
    block
    -0.45
     poda
    -0.42
     Clover
    -0.42
    BLOCK
    -0.42
     Dixie
    -0.42
    igshid
    -0.41
    ernalia
    -0.41
    POSITIVE LOGITS
     warranty
    1.78
     guarantee
    1.51
     warranties
    1.49
     Warranty
    1.49
    warranty
    1.40
     Guarantee
    1.40
    Warranty
    1.35
     garantie
    1.32
     WARRANTY
    1.31
     Garantie
    1.28
    Activations Density 0.127%

    No Known Activations