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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 9493
    Prev
    Next
    INDEX
    Explanations

    email addresses, particularly those using Gmail

    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
    Portail
    -0.85
    出版年
    -0.80
    modelBuilder
    -0.76
     snippetHide
    -0.74
    ductory
    -0.72
    setDo
    -0.71
    Portály
    -0.69
    addCriterion
    -0.67
     AssemblyCulture
    -0.66
    ngdoc
    -0.65
    POSITIVE LOGITS
    gmail
    2.79
     gmail
    1.75
    Gmail
    1.36
    hotmail
    1.34
     Gmail
    1.31
    yahoo
    1.24
    blogspot
    1.14
    aol
    0.95
    appspot
    0.92
    comcast
    0.79
    Activations Density 0.036%

    No Known Activations