© 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-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 1482
    Prev
    Next
    INDEX
    Explanations

    future actions and intentions stated in the document

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

    Sentences starting with "We will" or "It"

    np_acts-logits-general · gemini-2.0-flash

    will followed by action verb

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    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
    kháu
    -0.55
     Савезне
    -0.49
    TagMode
    -0.48
     Administrativna
    -0.45
     Italijani
    -0.45
     Italijanski
    -0.44
    Aholisi
    -0.40
    AISSEE
    -0.39
    ]=>
    -0.38
     Италијани
    -0.35
    POSITIVE LOGITS
    ValueStyle
    0.66
     pleaſure
    0.63
    ſelf
    0.60
     purpoſe
    0.57
    endpush
    0.56
     myſelf
    0.51
     ſtate
    0.50
     Matter
    0.50
    Matter
    0.50
     Diſ
    0.49
    Activations Density 0.661%

    No Known Activations