© 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. 24-GEMMASCOPE-RES-16K
    11. 571
    Prev
    Next
    INDEX
    Explanations

    attributes and characteristics related to products and design quality

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

    Blending in or being unnoticeable

    np_acts-logits-general · gemini-2.0-flash

    blending and concealment

    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
    SequentialGroup
    -0.46
    OneToMany
    -0.38
     retenir
    -0.37
     Reinhold
    -0.36
    碱
    -0.35
    AddTagHelper
    -0.34
     estamp
    -0.34
     yPos
    -0.33
    isNotNull
    -0.33
    日閲覧
    -0.33
    POSITIVE LOGITS
     inconspicuous
    0.82
     seamlessly
    0.78
     indistingu
    0.76
     blends
    0.75
     blending
    0.74
     seamless
    0.73
     concealment
    0.69
     blended
    0.69
    stealth
    0.67
     Blend
    0.65
    Activations Density 0.307%

    No Known Activations