© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 0-GEMMASCOPE-RES-16K
    6. 2293
    Prev
    Next
    INDEX
    Explanations

    terms associated with "free" offerings or services

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_0/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     TestBed
    -0.65
     Greet
    -0.61
     AIS
    -0.58
     Darn
    -0.57
     Crud
    -0.50
    disposing
    -0.50
     greet
    -0.50
     Indications
    -0.49
    RuleContext
    -0.49
    发表于
    -0.49
    POSITIVE LOGITS
     free
    1.14
     libre
    1.04
     Free
    1.02
    Free
    0.99
    自由
    0.98
     libres
    0.97
    free
    0.95
     freien
    0.91
     FREE
    0.88
     szabad
    0.85
    Activations Density 0.217%

    No Known Activations