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-2-2B
    4. Residual Stream - 16k
    5. 11-GEMMASCOPE-RES-16K
    6. 6814
    Prev
    Next
    INDEX
    Explanations

    phrases associated with qualitative research and its application in understanding human experiences and conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ={`/
    -0.50
     licht
    -0.42
    )」
    -0.42
    poň
    -0.42
    idez
    -0.40
     fece
    -0.40
     Og
    -0.40
     ']
    -0.40
    him
    -0.40
     address
    -0.40
    POSITIVE LOGITS
    NameInMap
    0.81
     BoxFit
    0.78
     Италијани
    0.78
    ьаж
    0.76
     kræ
    0.75
     للمعارف
    0.75
    Autoritní
    0.75
     ProtoMessage
    0.74
    complexType
    0.69
    IVEREF
    0.68
    Activations Density 0.551%

    No Known Activations