© 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. 2-GEMMASCOPE-RES-16K
    11. 8127
    Prev
    Next
    INDEX
    Explanations

    colons and phrases indicating hierarchical or referential structures

    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
     адрес
    -0.37
    Appropriate
    -0.36
     незавершена
    -0.35
     kişinin
    -0.35
    AndEndTag
    -0.35
    scanf
    -0.34
     Appropriate
    -0.34
     rendah
    -0.34
    respect
    -0.33
    fris
    -0.33
    POSITIVE LOGITS
     AssemblyVersion
    0.63
     ProtoMessage
    0.62
    WithIOException
    0.62
     createSlice
    0.60
    enablog
    0.60
    MigrationBuilder
    0.60
     intStringLen
    0.59
     EconPapers
    0.59
    setVerticalGroup
    0.58
     ſte
    0.57
    Activations Density 0.085%

    No Known Activations