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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 20-GEMMASCOPE-RES-131K
    6. 14211
    Prev
    Next
    INDEX
    Explanations

    terms related to chemical precursors and their reactions in the synthesis of metal compounds

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

    metal sulfide complexes

    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
    ValueStyle
    -0.63
    MigrationBuilder
    -0.60
     ✭✭
    -0.49
    İstinadlar
    -0.49
    principalColumn
    -0.49
     cóc
    -0.48
     myſelf
    -0.48
    HomeAsUpEnabled
    -0.48
    porters
    -0.47
     pleaſure
    -0.46
    POSITIVE LOGITS
     receptor
    0.44
     bentuk
    0.39
     Winaray
    0.39
    istoitu
    0.37
     form
    0.37
     forms
    0.36
    viato
    0.36
    frauen
    0.35
     cucharadas
    0.35
     Receptor
    0.35
    Activations Density 0.138%

    No Known Activations