© 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. 20-GEMMASCOPE-RES-16K
    11. 4515
    Prev
    Next
    INDEX
    Explanations

    instances of inclusion or mentions of included items within a context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    verbs like "include" and phrases involving inclusion or adding something.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     fraî
    -0.54
    <strong>
    -0.54
    mathbf
    -0.51
    pherds
    -0.50
    validators
    -0.50
    Validators
    -0.50
    pherd
    -0.50
    QMetaType
    -0.49
    NOPQRST
    -0.47
    GenerationType
    -0.47
    POSITIVE LOGITS
     Include
    1.21
     include
    1.20
     included
    1.15
    Include
    1.14
     inclusion
    1.14
    include
    1.14
     INCLUDE
    1.07
     includes
    1.05
    Included
    1.02
    included
    1.02
    Activations Density 0.108%

    No Known Activations