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. 4-GEMMASCOPE-RES-16K
    6. 12144
    Prev
    Next
    INDEX
    Explanations

    terms related to payment options and financial services

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    InjectAttribute
    -0.56
    DataAnnotations
    -0.54
    ẫy
    -0.54
    বহ
    -0.53
    Filmografia
    -0.53
     الحره
    -0.52
     ujednoznacz
    -0.52
    gov
    -0.51
     الفلك
    -0.49
    VersionUID
    -0.49
    POSITIVE LOGITS
     Krat
    0.63
    CBD
    0.61
    ColumnHeaders
    0.59
     CBD
    0.57
     vorüber
    0.55
    juana
    0.55
     nicotine
    0.53
    Jereo
    0.52
    (!__
    0.52
    ulemon
    0.51
    Activations Density 1.663%

    No Known Activations