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. 13501
    Prev
    Next
    INDEX
    Explanations

    the article "a" or "an" in various contexts

    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
     noemen
    -0.59
     partea
    -0.59
     daugiau
    -0.53
     quelconque
    -0.52
     provenant
    -0.50
     kask
    -0.49
     zaken
    -0.49
     eorum
    -0.49
     esplor
    -0.49
     vetorial
    -0.48
    POSITIVE LOGITS
    ########.
    0.93
     ProtoMessage
    0.89
     HasFactory
    0.87
     AssemblyCulture
    0.84
     MessageBoxIcon
    0.84
    LabelTagHelper
    0.80
    enumi
    0.79
    enumii
    0.79
    ngdoc
    0.78
    fromnode
    0.78
    Activations Density 0.065%

    No Known Activations