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. 7-GEMMASCOPE-RES-16K
    6. 4556
    Prev
    Next
    INDEX
    Explanations

    technical parameters related to computer architecture and configurations

    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
    TagMode
    -0.89
     kaarangay
    -0.66
    ContentAsync
    -0.66
     PhpStorm
    -0.63
    UrlResolution
    -0.62
    GeneratedCode
    -0.58
    mybatisplus
    -0.57
    ErrUnexpectedEOF
    -0.55
    unmodifiable
    -0.55
     PyLong
    -0.53
    POSITIVE LOGITS
    SequentialGroup
    0.62
    urlpatterns
    0.58
     Scarf
    0.55
    Filmografie
    0.53
    сылкі
    0.50
    BaseActivity
    0.49
    RenderAtEndOf
    0.48
     hidrá
    0.48
    vább
    0.46
    topi
    0.45
    Activations Density 0.531%

    No Known Activations