© 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. 4097
    Prev
    Next
    INDEX
    Explanations

    blocks of code involving file handling and resource management

    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
    WebElementEntity
    -0.81
     utafitiHapana
    -0.75
     EconPapers
    -0.72
    StructEnd
    -0.71
    Jeografia
    -0.71
     externi
    -0.69
    UserScript
    -0.68
    tanleria
    -0.67
    stdc
    -0.65
    tvguidetime
    -0.64
    POSITIVE LOGITS
    Closeable
    0.54
     Pexels
    0.47
     IDisposable
    0.44
     getResource
    0.43
    一股
    0.42
    UnitOfWork
    0.42
    一张
    0.41
    ButtonStyle
    0.41
     Pixabay
    0.40
     Unsplash
    0.39
    Activations Density 0.337%

    No Known Activations