Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Post
    5. 12-GEMMASCOPE-RES-1M
    6. 413
    Prev
    Next
    INDEX
    Explanations

    elements related to multipart requests or structures in programming

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_1m/average_l0_107
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    1,048,576
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    hydrates
    -0.64
     OFDb
    -0.58
    RTLD
    -0.52
    ]})
    -0.52
    ])):
    -0.51
    ymce
    -0.51
    UnsafeEnabled
    -0.49
    iorna
    -0.49
    UnknownFields
    -0.49
     sqlalchemy
    -0.47
    POSITIVE LOGITS
     AssemblyTitle
    0.68
     Audiodateien
    0.56
    íncia
    0.55
    HostException
    0.54
    ůli
    0.54
    MemoryWarning
    0.53
     وتسجيلات
    0.53
    تفسير
    0.52
    VIAF
    0.52
    くれる
    0.52
    Activations Density 0.000%

    No Known Activations