© 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. 2-GEMMASCOPE-RES-16K
    6. 8264
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "transferred" and its variants in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    bufio
    -0.41
    afficheront
    -0.39
     cuota
    -0.38
    合物
    -0.37
     ſche
    -0.37
     cuotas
    -0.36
     revenus
    -0.36
     Bedienung
    -0.36
     getList
    -0.36
     rebuttal
    -0.36
    POSITIVE LOGITS
     transferred
    1.61
    Transferred
    1.34
     transferring
    1.31
     transmitted
    1.27
     transfers
    1.04
     transfé
    1.03
     Transfers
    1.02
     transferir
    1.02
     Transfer
    0.98
     transferable
    0.96
    Activations Density 0.277%

    No Known Activations