Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 82623
    Prev
    Next
    INDEX
    Explanations

    references and their usage in React programming

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

    ref and name attributes

    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
     ब्रेकडाउन
    -0.98
    bootstrapcdn
    -0.88
     الحره
    -0.88
     queſta
    -0.84
    djangoproject
    -0.84
     nonUne
    -0.81
    iſchen
    -0.80
    TagMode
    -0.77
    iſen
    -0.77
    ſſung
    -0.77
    POSITIVE LOGITS
     useRef
    0.69
    Ref
    0.40
     Ref
    0.38
     ref
    0.36
     ElementRef
    0.36
    ref
    0.32
    ViewChild
    0.30
    ("")]
    
    0.28
    sqcup
    0.27
    )
    0.27
    Activations Density 0.005%

    No Known Activations