Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 12504
    Prev
    Next
    INDEX
    Explanations

    mentions of social media platforms and encourage following or engagement on these platforms

    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
    +#+#
    -0.72
     BoxFit
    -0.65
    ContentLoaded
    -0.64
    ContentAlignment
    -0.61
    GeneratedCode
    -0.61
    NgModule
    -0.60
     >=",
    -0.60
     convertView
    -0.60
     ExecuteAsync
    -0.59
    RenderAtEndOf
    -0.59
    POSITIVE LOGITS
     Twitter
    2.32
     Facebook
    2.29
     Instagram
    2.09
    Twitter
    2.04
    Facebook
    2.03
     twitter
    1.99
     facebook
    1.93
     LinkedIn
    1.88
    Instagram
    1.84
     instagram
    1.76
    Activations Density 0.241%

    No Known Activations