© 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-2-2B
    4. Residual Stream - 16k
    5. 7-GEMMASCOPE-RES-16K
    6. 6009
    Prev
    Next
    INDEX
    Explanations

    specific details related to technical specifications and characteristics of devices and their functionalities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ConstraintMaker
    -0.87
     estekak
    -0.64
     Мексичка
    -0.62
     يتيمه
    -0.56
    Zdroje
    -0.55
    reathe
    -0.54
    adillas
    -0.53
    Referencie
    -0.52
     pop
    -0.52
     plexus
    -0.52
    POSITIVE LOGITS
    yorsunuz
    0.52
    omitempty
    0.51
    Ded
    0.50
    SharedCtor
    0.48
     RTA
    0.47
     Horacio
    0.46
     affordability
    0.45
    rawDesc
    0.45
    きた
    0.45
    stdc
    0.45
    Activations Density 0.092%

    No Known Activations