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. 4-GEMMASCOPE-RES-16K
    6. 3099
    Prev
    Next
    INDEX
    Explanations

    references to variables in programming contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     تضيفلها
    -0.80
    panou
    -0.69
     Absch
    -0.68
     Dorsey
    -0.60
    CopyTo
    -0.59
     Finish
    -0.58
    сылкі
    -0.57
    TargetApi
    -0.57
     Iš
    -0.57
    looks
    -0.56
    POSITIVE LOGITS
     variables
    2.49
     Variables
    2.40
     Variable
    2.35
     variable
    2.35
    Variables
    2.27
     VARIABLE
    2.25
    Variable
    2.25
    variable
    2.19
    variables
    2.15
     VARIABLES
    2.06
    Activations Density 0.118%

    No Known Activations