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. 3721
    Prev
    Next
    INDEX
    Explanations

    functions related to exponential growth or decay

    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
    Enllaços
    -0.55
    arrive
    -0.51
    aronne
    -0.51
    Hashes
    -0.51
    Enciclopedia
    -0.50
     yarış
    -0.49
    ת
    -0.49
    indere
    -0.48
    yntaxException
    -0.48
    ศึกษา
    -0.48
    POSITIVE LOGITS
     Supervisors
    1.12
     supervisor
    1.10
    Supervisor
    1.05
     Supervision
    1.04
     Supervisor
    1.02
     supervisors
    1.02
     BoxDecoration
    1.00
    Supervis
    0.99
     supervision
    0.93
     Supervis
    0.90
    Activations Density 0.065%

    No Known Activations