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. 18-GEMMASCOPE-RES-16K
    6. 10240
    Prev
    Next
    INDEX
    Explanations

    references to "steroids" and related biochemical terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
     صوتيه
    -0.57
    mybatisplus
    -0.57
    PARTMENT
    -0.57
     pensato
    -0.56
     nakalista
    -0.56
    escrit
    -0.54
     <<<<<<<<<<<<<<
    -0.53
    ة
    -0.53
    cherichia
    -0.53
     iconst
    -0.52
    POSITIVE LOGITS
    ring
    0.71
     ster
    0.69
    éviter
    0.61
    dataclass
    0.59
     ricor
    0.58
    setViewportView
    0.57
    TestTools
    0.57
    Ár
    0.57
    rencia
    0.56
    quelles
    0.56
    Activations Density 0.214%

    No Known Activations