© 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. 2-GEMMASCOPE-RES-16K
    6. 8178
    Prev
    Next
    INDEX
    Explanations

    references to what is considered normal in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 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
     Signalez
    -0.52
    躇
    -0.44
    Norm
    -0.39
     retailer
    -0.39
     norm
    -0.38
    suited
    -0.38
    prehen
    -0.37
     Normalized
    -0.36
    equ
    -0.36
    อย่าง
    -0.36
    POSITIVE LOGITS
     normal
    2.23
    normal
    2.03
    Normal
    1.95
     Normal
    1.85
     NORMAL
    1.68
    NORMAL
    1.45
    正常
    1.44
     normales
    1.41
     normale
    1.36
     normalen
    1.30
    Activations Density 0.055%

    No Known Activations