© 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-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 102684
    Prev
    Next
    INDEX
    Explanations

    phrases and terms related to informed consent and ethical considerations in research

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

    informed consent

    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-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
     Administrativna
    -0.57
     صوتيه
    -0.54
    Cyfarwyddwr
    -0.52
    AndroidJUnit
    -0.52
     gynhyrchwyd
    -0.48
    estroyer
    -0.48
    enderror
    -0.48
     Chriftian
    -0.47
     Италијани
    -0.47
    bootstrapcdn
    -0.47
    POSITIVE LOGITS
     consent
    0.60
    consent
    0.46
     Consent
    0.45
    Consent
    0.45
     permission
    0.44
     Einwilligung
    0.40
    拔
    0.38
     consenting
    0.37
     consents
    0.36
    তথ্যসূত্র
    0.35
    Activations Density 0.057%

    No Known Activations