© 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. 2-GEMMASCOPE-RES-16K
    6. 8790
    Prev
    Next
    INDEX
    Explanations

    references to locations or accessibility in a global context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    s
    -0.72
     faut
    -0.67
    tis
    -0.64
     disambiguazione
    -0.61
    la
    -0.59
    q
    -0.56
    ps
    -0.56
     mir
    -0.55
    为
    -0.54
    d
    -0.54
    POSITIVE LOGITS
     anywhere
    2.75
    anywhere
    2.71
     Anywhere
    2.62
     everywhere
    2.56
    everywhere
    2.46
     Everywhere
    2.39
     nowhere
    2.27
    Anywhere
    2.25
    Everywhere
    2.09
     partout
    2.01
    Activations Density 0.105%

    No Known Activations