Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 12-GEMMASCOPE-RES-16K
    6. 5328
    Prev
    Next
    INDEX
    Explanations

    references to gambling or financial transactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_12/width_16k/average_l0_130
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Życiorys
    -0.46
     artikkelen
    -0.44
     investments
    -0.43
     bowiem
    -0.43
    ร่วม
    -0.42
     își
    -0.40
     szczegó
    -0.40
    서는
    -0.40
    篇文章
    -0.40
     Einfluß
    -0.40
    POSITIVE LOGITS
    #+#
    0.56
    posedge
    0.47
    OGND
    0.45
    TagHelpers
    0.45
    Jeografia
    0.43
    PyExc
    0.43
     صوتيه
    0.43
    添
    0.41
    */].
    0.41
    Salta
    0.41
    Activations Density 0.384%

    No Known Activations