© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 4-GEMMASCOPE-RES-16K
    6. 12588
    Prev
    Next
    INDEX
    Explanations

    mathematical operators and symbols used in equations

    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
    Erreferentziak
    -0.59
     Benn
    -0.56
    lolo
    -0.56
     ActionListener
    -0.54
     createSlice
    -0.53
    anik
    -0.51
    روط
    -0.50
    бель
    -0.49
    mort
    -0.49
    arrête
    -0.48
    POSITIVE LOGITS
    ymce
    0.96
     YS
    0.85
     Ys
    0.85
    Yn
    0.80
     YR
    0.78
     getY
    0.78
     Yor
    0.78
    yyy
    0.78
     YP
    0.77
    ytt
    0.76
    Activations Density 0.619%

    No Known Activations