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. 24-GEMMASCOPE-RES-16K
    6. 14091
    Prev
    Next
    INDEX
    Explanations

    phrases and words related to durability and resistance in products

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

    Prevents/avoidance of damage or entanglement

    np_acts-logits-general · gemini-2.0-flash

    material degradation or damage

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     CreateTagHelper
    -0.56
    tvguidetime
    -0.55
    omeric
    -0.54
     ویکی‌پدیا
    -0.53
    setViewName
    -0.51
    unsplash
    -0.50
     exon
    -0.50
    ExecutionContext
    -0.49
     mema
    -0.48
    éos
    -0.48
    POSITIVE LOGITS
     scratch
    0.84
    WriteBarrier
    0.76
    scratch
    0.74
     scratching
    0.73
     Scratch
    0.69
     scratches
    0.69
     snag
    0.68
    Scratch
    0.65
     scrat
    0.64
    :✨
    0.63
    Activations Density 0.204%

    No Known Activations