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. 34-GEMMASCOPE-RES-16K
    6. 10925
    Prev
    Next
    INDEX
    Explanations

    references to sources and further information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 34-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_34/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.34.hook_resid_post
    Hook Layer
    34
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     للاسماء
    -0.85
    complexContent
    -0.56
    ########.
    -0.56
    ValueStyle
    -0.55
    tanleria
    -0.52
     ModelExpression
    -0.52
    CppMethod
    -0.51
     kasarigan
    -0.49
    ंदीखरीदारी
    -0.48
    Życiorys
    -0.47
    POSITIVE LOGITS
     HERE
    1.56
     here
    1.52
    HERE
    1.36
    here
    1.23
     Here
    1.10
     aquí
    1.08
     здесь
    1.01
    Here
    1.01
     aqui
    0.99
     aici
    0.98
    Activations Density 0.475%

    No Known Activations