© 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-2-2B
    4. Residual Stream - 16k
    5. 1-GEMMASCOPE-RES-16K
    6. 13979
    Prev
    Next
    INDEX
    Explanations

    references to formats and formatting in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     rospy
    -0.56
    μβρίου
    -0.55
     aggiunge
    -0.53
    BooleanField
    -0.53
     addSubview
    -0.53
     olímp
    -0.52
    NTSTATUS
    -0.52
    PDOException
    -0.52
    UnusedPrivate
    -0.50
     &'
    -0.50
    POSITIVE LOGITS
     format
    4.68
     Format
    4.28
     formats
    4.02
    Format
    3.90
     FORMAT
    3.88
    format
    3.81
     Formats
    3.58
    FORMAT
    3.36
     formato
    3.17
    formats
    3.02
    Activations Density 0.081%

    No Known Activations