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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 4488
    Prev
    Next
    INDEX
    Explanations

    function and method declarations in code

    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
    oredCriteria
    -0.68
    ########.
    -0.61
    +#+#
    -0.59
    CppMethod
    -0.57
    andExpect
    -0.56
    sizeCache
    -0.55
    TintMode
    -0.55
    FunctionFlags
    -0.53
     IMDG
    -0.52
    Abitanti
    -0.52
    POSITIVE LOGITS
    ArgsConstructor
    0.78
     CreateTagHelper
    0.64
     initWith
    0.52
    ]<<
    0.51
    一心
    0.51
     Rad
    0.50
    AfterClass
    0.49
    теристика
    0.49
    ]<<"
    0.49
    χι
    0.48
    Activations Density 0.186%

    No Known Activations