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. 5-GEMMASCOPE-RES-16K
    6. 11150
    Prev
    Next
    INDEX
    Explanations

    words related to "corruption" and terms starting with "cor."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Theſe
    -1.16
     Anſ
    -1.16
     Efq
    -1.13
     Monfieur
    -1.12
     Houſe
    -1.08
     uſe
    -1.04
     myſelf
    -1.03
     Diſ
    -1.02
     ſta
    -1.01
     faſt
    -0.99
    POSITIVE LOGITS
     Cor
    2.31
     cor
    2.17
    Cor
    2.15
    cor
    2.08
     COR
    2.08
    COR
    1.91
     Kor
    1.66
     kor
    1.63
     Corbett
    1.56
     Corr
    1.52
    Activations Density 0.081%

    No Known Activations