© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 28-GEMMASCOPE-RES-16K
    11. 9564
    Prev
    Next
    INDEX
    Explanations

    conditional statements and hypothetical scenarios

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

    "if" followed by a word indicating necessity

    np_acts-logits-general · gemini-2.0-flash

    if necessary or needed

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    WriteBarrier
    -0.49
     wikipagina
    -0.46
    setViewportView
    -0.42
    complexType
    -0.42
     ***!
    -0.41
    tagHelperRunner
    -0.41
     JsonResponse
    -0.41
    fören
    -0.41
    attutto
    -0.40
    StoryboardSegue
    -0.40
    POSITIVE LOGITS
     necessary
    1.85
     needed
    1.70
    necessary
    1.56
    needed
    1.48
    必要
    1.46
     Necessary
    1.36
     Needed
    1.33
    Necessary
    1.30
     need
    1.29
     필요
    1.29
    Activations Density 0.282%

    No Known Activations