© 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. 37-GEMMASCOPE-RES-16K
    6. 5506
    Prev
    Next
    INDEX
    Explanations

    information related to programming and technical specifications concerning ports, connections, and data management

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 37-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_37/width_16k/average_l0_124
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.37.hook_resid_post
    Hook Layer
    37
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     MainAxisSize
    -0.47
    CompilerServices
    -0.44
    帖最后由
    -0.38
    ConstraintMaker
    -0.37
     lccn
    -0.37
     numerus
    -0.36
     Pesquisa
    -0.35
    脚注の使い方
    -0.35
    ímica
    -0.34
    fjspx
    -0.33
    POSITIVE LOGITS
     port
    3.44
     Port
    3.33
    Port
    3.13
     PORT
    3.09
    port
    3.02
     ports
    2.81
    PORT
    2.80
     Ports
    2.56
    ポート
    2.47
    ports
    2.44
    Activations Density 0.811%

    No Known Activations