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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 2-GEMMASCOPE-RES-16K
    6. 2088
    Prev
    Next
    INDEX
    Explanations

    terms related to the act of building or creating, particularly in a programming or mathematical context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Administrativna
    -0.80
     BoxFit
    -0.79
     /\.
    -0.78
    tvguidetime
    -0.76
    WebVitals
    -0.76
     AssemblyCulture
    -0.75
     UIFont
    -0.70
     HasFactory
    -0.70
    Jereo
    -0.69
     Rhiz
    -0.69
    POSITIVE LOGITS
     construct
    2.99
     Construct
    2.78
    Construct
    2.59
    construct
    2.57
     constructed
    2.51
     constructs
    2.50
     constructing
    2.46
    constructed
    2.20
     Constructs
    2.04
     Constructed
    2.02
    Activations Density 0.082%

    No Known Activations