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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 9-GEMMASCOPE-RES-131K
    6. 98236
    Prev
    Next
    INDEX
    Explanations

    markup and structural elements commonly used in HTML documents

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

    HTML tags and attributes

    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-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
     kasarigan
    -0.67
    ISupport
    -0.66
    SequentialGroup
    -0.63
    esModule
    -0.61
     محفوظة
    -0.60
    BeginInit
    -0.60
    __':
    
    -0.60
    Hentet
    -0.60
    BibitemShut
    -0.59
    ParallelGroup
    -0.59
    POSITIVE LOGITS
    UnusedPrivate
    0.36
    untamiento
    0.36
    ="@
    0.36
    цездатний
    0.35
     crossorigin
    0.35
    bootstrapcdn
    0.35
     ✭✭
    0.33
    GenerationType
    0.33
    тъ
    0.32
    енча
    0.32
    Activations Density 0.060%

    No Known Activations