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. 10-GEMMASCOPE-RES-16K
    6. 8860
    Prev
    Next
    INDEX
    Explanations

    expressions of passion and a drive to make a positive difference in people's lives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     am
    -0.47
     $\
    -0.47
     six
    -0.46
     specific
    -0.46
     tạp
    -0.45
     co
    -0.45
     seg
    -0.44
     $
    -0.43
    ски
    -0.43
    teen
    -0.43
    POSITIVE LOGITS
    GEBURTSDATUM
    0.92
    脚注の使い方
    0.91
    verwijspagina
    0.91
     <>",
    0.84
    protoimpl
    0.79
     Phry
    0.77
     doubtnut
    0.76
    rungsseite
    0.76
     виправивши
    0.76
    Personendaten
    0.73
    Activations Density 0.251%

    No Known Activations