© 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. 20-GEMMASCOPE-RES-16K
    6. 15830
    Prev
    Next
    INDEX
    Explanations

    statements that explain reasoning or justification

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     initComponents
    -0.57
    colgroup
    -0.55
    RegressionTest
    -0.53
    SharedDtor
    -0.53
    lapsingToolbar
    -0.49
     विश्वसनीयता
    -0.47
     ligiloj
    -0.47
    soever
    -0.47
    Diweddarwch
    -0.47
    msgSender
    -0.47
    POSITIVE LOGITS
    dafx
    0.49
    ]]);
    0.47
    发表于
    0.40
    '];?>
    0.38
    }})
    0.36
    \}=\
    0.36
    ))->
    0.36
     تمر
    0.36
    '},
    
    0.35
     easier
    0.35
    Activations Density 0.259%

    No Known Activations