© 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. 25-GEMMASCOPE-RES-16K
    6. 1232
    Prev
    Next
    INDEX
    Explanations

    questions and inquiries about various topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    imanapun
    -0.49
    either
    -0.49
    hichever
    -0.48
    담
    -0.48
    enseits
    -0.48
    Superview
    -0.48
     either
    -0.47
     epä
    -0.46
    Bitte
    -0.46
    olah
    -0.45
    POSITIVE LOGITS
     Does
    1.08
     We
    1.05
     Are
    1.00
     You
    1.00
     Should
    0.98
     They
    0.98
     Did
    0.96
     Do
    0.93
     Happens
    0.86
     Will
    0.84
    Activations Density 0.191%

    No Known Activations