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-2-2B
    4. Residual Stream - 16k
    5. 15-GEMMASCOPE-RES-16K
    6. 2770
    Prev
    Next
    INDEX
    Explanations

    indicators of false responses or inaccuracies in information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Wikimedijinoj
    -0.58
    DebuggerNonUser
    -0.56
     或
    -0.51
     تعدى
    -0.50
     definitely
    -0.49
     or
    -0.48
     bete
    -0.47
    Якщо
    -0.46
    Chham
    -0.45
    Према
    -0.45
    POSITIVE LOGITS
    BeginInit
    0.84
     שוליים
    0.64
    ]');
    0.64
    ]='\
    0.64
    >';
    
    0.62
    ](#
    0.62
     فريبيس
    0.62
    новништво
    0.61
     discusses
    0.61
    ISupport
    0.60
    Activations Density 0.058%

    No Known Activations