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. 35-GEMMASCOPE-RES-16K
    6. 7438
    Prev
    Next
    INDEX
    Explanations

    terms associated with military units and operations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 35-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_35/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.35.hook_resid_post
    Hook Layer
    35
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    出版年
    -0.74
     للمعارف
    -0.71
     <<<<<<<<<<<<<<
    -0.70
     defaultstate
    -0.69
     CreateTagHelper
    -0.68
     typelib
    -0.67
     незавершена
    -0.65
    AddTagHelper
    -0.60
    Бахар
    -0.60
    UnusedPrivate
    -0.59
    POSITIVE LOGITS
     base
    0.85
     bases
    0.82
     Base
    0.71
    base
    0.69
    bases
    0.65
    基地
    0.62
     Bases
    0.61
    Base
    0.60
    Bases
    0.59
     camp
    0.58
    Activations Density 0.384%

    No Known Activations