© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 38-GEMMASCOPE-RES-16K
    11. 15286
    Prev
    Next
    INDEX
    Explanations

    programming terms and concepts related to networking and data connections

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 38-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_38/width_16k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.38.hook_resid_post
    Hook Layer
    38
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    CompilerServices
    -0.42
     MainAxisSize
    -0.40
    帖最后由
    -0.36
     numerus
    -0.34
    脚注の使い方
    -0.33
    ímica
    -0.33
    ConstraintMaker
    -0.32
     lccn
    -0.31
    DebuggerNonUser
    -0.31
    Inhalt
    -0.30
    POSITIVE LOGITS
     port
    3.45
     Port
    3.34
    Port
    3.16
     PORT
    3.13
    port
    3.05
    PORT
    2.84
     ports
    2.81
     Ports
    2.56
     POR
    2.50
    ポート
    2.48
    Activations Density 1.008%

    No Known Activations