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. 5-GEMMASCOPE-RES-16K
    6. 16264
    Prev
    Next
    INDEX
    Explanations

    specific types of antibodies used in various immunological assays

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    +:+
    -0.68
     favourably
    -0.60
     createState
    -0.59
    garmin
    -0.58
     referenties
    -0.56
    ).]
    -0.55
     INTERESAR
    -0.54
    Viungo
    -0.53
    inetics
    -0.53
    isitions
    -0.52
    POSITIVE LOGITS
    CreateMap
    0.57
    MigrationBuilder
    0.52
     JADX
    0.52
    SerializeField
    0.50
     jadx
    0.49
     Klass
    0.48
     Riproduzione
    0.47
     nawr
    0.45
    localObject
    0.44
    PreferredItem
    0.43
    Activations Density 0.463%

    No Known Activations