© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 3-GEMMASCOPE-RES-16K
    6. 13170
    Prev
    Next
    INDEX
    Explanations

    words related to the concept of presenting or displaying information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    PreferredItem
    -0.74
    medriver
    -0.70
    makedirs
    -0.70
     onResponse
    -0.69
     OkHttpClient
    -0.69
    iastes
    -0.68
    +#+#
    -0.67
     useRouter
    -0.64
     propOrder
    -0.62
    anasia
    -0.61
    POSITIVE LOGITS
     presenting
    1.58
     Presenting
    1.51
     presented
    1.51
     presentation
    1.50
    Presenting
    1.48
     presents
    1.44
    presented
    1.40
     presenta
    1.39
    presentation
    1.36
     Presents
    1.36
    Activations Density 0.239%

    No Known Activations