© 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. 1289
    Prev
    Next
    INDEX
    Explanations

    procedures and steps related to technology upgrades and migrations

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

    Transferring data, systems, or properties

    np_acts-logits-general · gemini-2.0-flash

    transfer and migration

    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
     ModelExpression
    -0.56
    SequentialGroup
    -0.53
     pleaſure
    -0.51
     ſche
    -0.51
     anſ
    -0.46
     desmotivaciones
    -0.45
    RenderAtEndOf
    -0.44
     ſtate
    -0.44
     OFDb
    -0.44
     myſelf
    -0.44
    POSITIVE LOGITS
     transferred
    0.61
     migrated
    0.53
     transferring
    0.52
     migrating
    0.50
     transfers
    0.50
     migrate
    0.50
     transfer
    0.49
    转移
    0.46
     Transfer
    0.46
    Transfer
    0.46
    Activations Density 0.374%

    No Known Activations