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-2-9B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 7328
    Prev
    Next
    INDEX
    Explanations

    references to astronomical phenomena

    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
    $_['
    -0.54
    UnusedPrivate
    -0.48
    +#+#
    -0.48
    StandardCharsets
    -0.47
    )))));
    -0.42
    WriteTagHelper
    -0.42
    mögen
    -0.40
    MathML
    -0.40
    PerformLayout
    -0.40
    SerializedName
    -0.39
    POSITIVE LOGITS
    Personendaten
    0.66
     StatelessWidget
    0.52
    يكب
    0.49
     насељу
    0.46
    SharedDtor
    0.44
     ComVisible
    0.43
    ViewFeatures
    0.43
    qü
    0.41
    Tikang
    0.41
    tanleria
    0.40
    Activations Density 0.068%

    No Known Activations