© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 7-GEMMASCOPE-RES-16K
    11. 15957
    Prev
    Next
    INDEX
    Explanations

    instances of the word "manifest" and its variations, indicating a focus on expressions or occurrences of something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_7/width_16k/average_l0_92
    Prompts (Dashboard)
    24,576 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
    BeginContext
    -0.59
     ویکی‌پدی
    -0.55
    DoubleQuotes
    -0.53
     незавершена
    -0.48
     uska
    -0.47
     remet
    -0.45
    TagMode
    -0.45
     noDo
    -0.44
    المناصب
    -0.44
    msgTypes
    -0.44
    POSITIVE LOGITS
     manifested
    1.45
     Manifest
    1.42
     manifest
    1.41
     manifesting
    1.39
     manifestation
    1.38
     manifests
    1.37
    manifest
    1.37
    Manifest
    1.29
     manifestations
    1.29
    manif
    1.16
    Activations Density 0.325%

    No Known Activations