© 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. 38-GEMMASCOPE-RES-16K
    6. 14595
    Prev
    Next
    INDEX
    Explanations

    technical terms and concepts related to computer programming and networking

    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
     مرئيه
    -0.46
    HomeAsUpEnabled
    -0.40
    ]")]
    -0.40
    NegativeButton
    -0.36
    bibfield
    -0.33
    reportWebVitals
    -0.32
    ])):
    -0.32
    …………………………………………
    -0.32
    ()));
    
    -0.31
    keyColumn
    -0.30
    POSITIVE LOGITS
    balleur
    0.57
     فريبيس
    0.56
                         
    0.54
                          
    0.52
    illère
    0.52
    RTSC
    0.50
    pleft
    0.50
    Pautan
    0.49
                           
    0.49
    StackSize
    0.49
    Activations Density 0.481%

    No Known Activations