© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 3325
    Prev
    Next
    INDEX
    Explanations

    comparative phrases that emphasize preference or contrast between options

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    words indicating contrast or comparison, such as "rather than".

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi
    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
    tagHelperRunner
    -0.69
     '\\;'
    -0.56
     doInBackground
    -0.56
    🔕
    -0.54
    InputTagHelper
    -0.53
    ༘
    -0.53
    UnusedPrivate
    -0.52
    ArgumentParser
    -0.51
     houſe
    -0.49
    bootstrapcdn
    -0.49
    POSITIVE LOGITS
    而不是
    0.53
    而非
    0.52
     necesariamente
    0.45
     zamiast
    0.44
    than
    0.44
     necessariamente
    0.44
    IsContent
    0.44
    Rather
    0.42
    あくまで
    0.42
     Rather
    0.42
    Activations Density 0.221%

    No Known Activations