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. 103438
    Prev
    Next
    INDEX
    Explanations

    references to "PhysRev" documents or sections within scientific literature, particularly in the context of Unity programming

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

    PhysRevB, PhysRevX, PhysRevApplied citations

    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
    ReusableCell
    -0.58
    MemoryWarning
    -0.56
    userdetails
    -0.50
     typelib
    -0.48
     InputDecoration
    -0.48
    findpost
    -0.48
    Personendaten
    -0.47
    rdi
    -0.43
    StructEnd
    -0.43
     Roskov
    -0.43
    POSITIVE LOGITS
     nahilalakip
    1.67
    Referències
    1.02
     صوتيه
    0.98
    flink
    0.84
     UnityEditor
    0.81
    ERVIS
    0.77
    PhysRev
    0.76
     ziren
    0.65
    OrBuilder
    0.61
     تكبرها
    0.56
    Activations Density 0.002%

    No Known Activations