© 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. 9621
    Prev
    Next
    INDEX
    Explanations

    phrases indicating causation or reasoning

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

    Following "this", "that", or "which"

    np_acts-logits-general · gemini-2.0-flash

    reasons why

    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
    MessageTagHelper
    -0.41
     ligiloj
    -0.40
    inSlope
    -0.38
    scriptcase
    -0.35
     TIC
    -0.34
     DPM
    -0.34
    ESTON
    -0.34
    cepan
    -0.33
     iParam
    -0.33
    TagMode
    -0.33
    POSITIVE LOGITS
     why
    2.13
     reason
    2.02
    why
    1.65
     pourquoi
    1.58
     reasons
    1.57
    Why
    1.53
     Why
    1.52
     varför
    1.47
     razón
    1.46
     hvorfor
    1.45
    Activations Density 0.429%

    No Known Activations