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. 19-GEMMASCOPE-RES-16K
    6. 2970
    Prev
    Next
    INDEX
    Explanations

    phrases related to medical treatment and withdrawal processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    HasIndex
    -0.54
    ylase
    -0.52
     urbanas
    -0.51
     Enlarged
    -0.51
    getColumnIndex
    -0.51
    Interpret
    -0.51
    antMatchers
    -0.50
    čius
    -0.50
     anisotropy
    -0.49
     المعيارى
    -0.49
    POSITIVE LOGITS
     transition
    2.16
     Transition
    1.87
    transition
    1.82
     transitions
    1.79
    Transition
    1.77
     gradual
    1.68
     transitioning
    1.66
     Transitions
    1.60
     transición
    1.52
     transitional
    1.51
    Activations Density 0.498%

    No Known Activations