© 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. 39-GEMMASCOPE-RES-16K
    6. 4586
    Prev
    Next
    INDEX
    Explanations

    names and identifiers related to individuals or entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 39-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_39/width_16k/average_l0_131
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.39.hook_resid_post
    Hook Layer
    39
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    accro
    -0.25
     spoloč
    -0.24
     Gottes
    -0.23
     jorden
    -0.19
     Hügel
    -0.18
     étro
    -0.18
     Bürgermeister
    -0.18
     dieťa
    -0.18
     pedig
    -0.18
     padang
    -0.18
    POSITIVE LOGITS
     MainAxisSize
    1.13
    
    1.10
     NSCoder
    1.09
     pinulongan
    1.05
     snippetHide
    1.05
    ðsíða
    1.02
    脚注の使い方
    0.99
    webElementGuid
    0.99
    ésultats
    0.98
     Infórmanos
    0.98
    Activations Density 0.846%

    No Known Activations