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-2-9B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 10253
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal terminology and concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    noinspection
    -0.46
    <?
    -0.45
    ългар
    -0.43
    Спољашње
    -0.43
    Enllaces
    -0.42
    قایناق‌لار
    -0.42
    onAttach
    -0.41
     OkHttpClient
    -0.41
     camry
    -0.39
     tarto
    -0.39
    POSITIVE LOGITS
    ChildScrollView
    0.52
    parsedMessage
    0.52
     فريبيس
    0.46
    Rptr
    0.45
    ItemBackground
    0.45
     Numerade
    0.44
     Rptr
    0.38
     Chalk
    0.38
    ErrUnexpectedEOF
    0.37
     betweenstory
    0.37
    Activations Density 0.966%

    No Known Activations