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. 21-GEMMASCOPE-RES-16K
    6. 953
    Prev
    Next
    INDEX
    Explanations

    components of video game titles and descriptions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Amino
    -0.56
    Amino
    -0.55
    StandardCharsets
    -0.54
     لينك
    -0.54
    IonicModule
    -0.54
     PhpStorm
    -0.54
    adaptiveStyles
    -0.52
     unprofessional
    -0.52
     amino
    -0.52
     profesional
    -0.51
    POSITIVE LOGITS
     isometric
    0.73
     mechanics
    0.65
     action
    0.64
    шаго
    0.59
     combat
    0.59
    oa̍t
    0.59
    ctible
    0.56
    φή
    0.55
     beginnetje
    0.55
     rpg
    0.54
    Activations Density 0.145%

    No Known Activations