© 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. 17-GEMMASCOPE-RES-16K
    6. 104
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions relating to scaling laws in physical systems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     doInBackground
    -0.45
    ​​​​
    -0.42
     Code
    -0.41
     interest
    -0.41
    Sub
    -0.41
    InvalidProtocol
    -0.41
     Sub
    -0.39
     sub
    -0.39
    emma
    -0.39
    cios
    -0.38
    POSITIVE LOGITS
     فريبيس
    0.83
    رشف
    0.79
     Autorizaciones
    0.79
    ichord
    0.75
    twimg
    0.74
     насељу
    0.73
    InitVars
    0.68
     صوتيه
    0.66
    ftagPool
    0.66
    rungsseite
    0.65
    Activations Density 1.303%

    No Known Activations