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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 10295
    Prev
    Next
    INDEX
    Explanations

    action verbs indicating creation, modification, or examination of objects or concepts

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

    followed by verbs like Defines, Creates, Checks, Sets

    np_acts-logits-general · gemini-2.0-flash

    verbs defining actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    存于互联网档案馆
    -0.55
     opinion
    -0.42
     or
    -0.41
    Preference
    -0.41
    Credential
    -0.40
    Plural
    -0.40
    Opinion
    -0.39
     houſe
    -0.39
    Scher
    -0.38
    Breadcrumb
    -0.38
    POSITIVE LOGITS
     للمعارف
    0.84
    roaches
    0.81
     propOrder
    0.75
    lishes
    0.73
    tifies
    0.73
     zijne
    0.72
    lizes
    0.71
    lains
    0.70
    cels
    0.70
    ixes
    0.70
    Activations Density 0.646%

    No Known Activations