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. 1-GEMMASCOPE-RES-16K
    6. 14888
    Prev
    Next
    INDEX
    Explanations

    statements that suggest or indicate consequences or interpretations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    zubauen
    -0.59
     Corcoran
    -0.58
     compréhen
    -0.58
    glers
    -0.57
    topf
    -0.55
    getBytes
    -0.55
    berapa
    -0.54
    emar
    -0.54
     Smal
    -0.54
    ButtonModule
    -0.54
    POSITIVE LOGITS
     implied
    1.60
     imply
    1.54
     implying
    1.35
     implies
    1.33
     inference
    1.25
     implication
    1.25
    imply
    1.23
     IMPLIED
    1.15
     infer
    1.14
     inferred
    1.14
    Activations Density 0.105%

    No Known Activations