© 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. 21-GEMMASCOPE-RES-16K
    11. 7108
    Prev
    Next
    INDEX
    Explanations

    phrases emphasizing repetition or recurrence in actions or events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     initial
    -0.32
    Initial
    -0.29
    initial
    -0.28
     Initial
    -0.28
     initially
    -0.27
     repente
    -0.27
    oiseau
    -0.26
    فتر
    -0.25
     originally
    -0.24
     вроде
    -0.24
    POSITIVE LOGITS
    again
    0.83
    今回も
    0.82
     again
    0.80
    Again
    0.80
     Again
    0.79
    ImageContext
    0.75
    __(/*!
    0.71
    rungsseite
    0.71
     AGAIN
    0.69
     nuevamente
    0.68
    Activations Density 0.349%

    No Known Activations