© 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-IT
    4. Residual Stream - 16k
    5. 9-GEMMASCOPE-RES-16K
    6. 10842
    Prev
    Next
    INDEX
    Explanations

    terms related to supervision and oversight in various contexts

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

    "supervision"

    np_acts-logits-general · gemini-2.0-flash

    supervision

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     resourceCulture
    -0.43
    Brendan
    -0.43
     nød
    -0.41
     ciudadana
    -0.40
    Enllaces
    -0.39
    ambassade
    -0.39
     læng
    -0.38
     køb
    -0.38
     politiker
    -0.38
     messengers
    -0.38
    POSITIVE LOGITS
     supervision
    1.66
     supervise
    1.53
     Supervision
    1.48
     supervis
    1.45
     supervised
    1.42
    Supervision
    1.40
     supervising
    1.38
     supervisory
    1.25
    supervised
    1.23
     supervisor
    1.21
    Activations Density 0.237%

    No Known Activations