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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 11238
    Prev
    Next
    INDEX
    Explanations

    references to visual experiences or observations

    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
    enderror
    -0.58
     faptul
    -0.57
    nodoc
    -0.55
    riwal
    -0.53
    fileupload
    -0.53
    fhir
    -0.52
    ství
    -0.51
    RTLU
    -0.50
     TWA
    -0.50
    ienda
    -0.49
    POSITIVE LOGITS
     seen
    1.47
    Seen
    1.36
     seeing
    1.33
    seen
    1.33
     saw
    1.31
     SEEN
    1.28
     Seen
    1.28
     sees
    1.26
     see
    1.21
    seeing
    1.19
    Activations Density 0.242%

    No Known Activations