© 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. 13261
    Prev
    Next
    INDEX
    Explanations

    references to artificial intelligence (AI) and its applications

    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
     layak
    -0.36
     consultato
    -0.36
    뀔
    -0.35
    }{%
    -0.35
    áne
    -0.33
     lande
    -0.33
    mosa
    -0.33
     leef
    -0.33
    åde
    -0.33
     valmist
    -0.32
    POSITIVE LOGITS
     AI
    3.00
    AI
    2.53
     artificial
    2.33
     Artificial
    2.33
     ai
    2.33
    Artificial
    2.19
    ai
    2.05
    artificial
    2.03
     Ai
    2.03
    Ai
    1.91
    Activations Density 0.229%

    No Known Activations