© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 24-GEMMASCOPE-RES-16K
    6. 5315
    Prev
    Next
    INDEX
    Explanations

    technical instructions and processes related to programming and software development

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    "then" or similar temporal adverbs

    np_acts-logits-general · gemini-2.0-flash

    sequencing verbs and adverbs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     }{@
    -0.62
     Vikipedi
    -0.57
    bootstrapcdn
    -0.55
     BoxFit
    -0.51
    BagLayout
    -0.50
     propOrder
    -0.49
    BeginContext
    -0.48
    TabView
    -0.48
    MessageState
    -0.47
    MarshalTo
    -0.47
    POSITIVE LOGITS
     then
    0.46
     later
    0.42
     sitten
    0.41
     потім
    0.40
     потом
    0.38
    Later
    0.38
    就好
    0.37
     zamiast
    0.36
    Then
    0.35
    就好了
    0.35
    Activations Density 0.709%

    No Known Activations