© 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. 18-GEMMASCOPE-RES-16K
    6. 2880
    Prev
    Next
    INDEX
    Explanations

    phrases related to programming and software functionality

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Comparing, contrasting, or differentiating things

    np_acts-logits-general · gemini-2.0-flash

    compare two

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ?!"
    -0.53
     "{}
    -0.52
    ?!?
    -0.51
    Specifically
    -0.50
     “[
    -0.50
     EVERYTHING
    -0.50
     REALLY
    -0.50
    specifically
    -0.49
     "[
    -0.49
    versus
    -0.49
    POSITIVE LOGITS
     pinulongan
    0.95
     upto
    0.95
     CreateTagHelper
    0.90
     atleast
    0.85
    upto
    0.82
    noOf
    0.82
    Datuak
    0.82
     viz
    0.80
    AntiForgeryToken
    0.79
     irrespective
    0.78
    Activations Density 0.695%

    No Known Activations