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. 9-GEMMASCOPE-RES-16K
    6. 8019
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "assign" and its variations in relation to tasks or values assigned

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Itoa
    -0.77
     /\.
    -0.76
    shund
    -0.73
     penyel
    -0.72
    gouv
    -0.71
     Barrow
    -0.70
    itattu
    -0.68
    inthians
    -0.67
     Kamal
    -0.67
    COOK
    -0.67
    POSITIVE LOGITS
     assign
    1.79
     assignment
    1.77
     assigns
    1.76
     assignments
    1.71
    ASSIGN
    1.67
     Assignments
    1.66
     Assign
    1.65
     ASSIGN
    1.63
     assigned
    1.60
     assig
    1.59
    Activations Density 0.090%

    No Known Activations