© 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-2-9B
    4. Residual Stream - 16k
    5. 10-GEMMASCOPE-RES-16K
    6. 6361
    Prev
    Next
    INDEX
    Explanations

    various forms of punctuation or separators in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_10/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    iſten
    -0.52
     صوتيه
    -0.50
    gnore
    -0.50
     snippetHide
    -0.49
     ſche
    -0.49
    esters
    -0.49
    iſt
    -0.49
    uisine
    -0.48
     initComponents
    -0.48
     esternos
    -0.48
    POSITIVE LOGITS
     subsequently
    0.42
     subsequent
    0.38
    jmniej
    0.36
     vēl
    0.35
    Welp
    0.35
     As
    0.35
     schließlich
    0.34
     appart
    0.34
     similarly
    0.34
     consequently
    0.33
    Activations Density 0.161%

    No Known Activations