© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 15-GEMMASCOPE-RES-16K
    11. 1986
    Prev
    Next
    INDEX
    Explanations

    numerical data and formatting attributes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    GEBURTSDATUM
    -1.02
    ReusableCell
    -0.96
    tagHelperRunner
    -0.93
    ValueStyle
    -0.90
     MaterialApp
    -0.88
     kaarangay
    -0.85
    Vidite
    -0.84
     Normdatei
    -0.83
     Signalez
    -0.82
    Tikang
    -0.79
    POSITIVE LOGITS
    放心
    0.46
    vit
    0.40
    greif
    0.39
     juga
    0.38
     jakie
    0.38
    рку
    0.37
    もう
    0.37
     Schrifts
    0.37
     тако
    0.36
    *[
    0.36
    Activations Density 0.444%

    No Known Activations