© 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. 13926
    Prev
    Next
    INDEX
    Explanations

    phrases related to quantifiable metrics or measurements with specific references

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

    introductory clauses or phrases that set context before presenting main information.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered 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
    SequentialGroup
    -0.55
    httphttps
    -0.44
    énario
    -0.43
     Manners
    -0.36
    migrationBuilder
    -0.35
     intr
    -0.33
     springfox
    -0.32
    HandlerContext
    -0.32
    ">//
    -0.31
     groupBox
    -0.31
    POSITIVE LOGITS
     AssemblyCulture
    0.63
     pouvoit
    0.61
     feroit
    0.60
     étoit
    0.55
    RotationOrder
    0.52
     متعلقه
    0.52
     prét
    0.52
     vœux
    0.52
     Numerade
    0.51
    OrNil
    0.51
    Activations Density 1.018%

    No Known Activations