© 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. 15422
    Prev
    Next
    INDEX
    Explanations

    specific terms or codes related to data entries, particularly focusing on identifiers and characteristics associated with them

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    IsContent
    -0.50
    RunWith
    -0.49
     BrowserModule
    -0.47
     inneren
    -0.45
    __":
    -0.44
     مشين
    -0.44
    ########.
    -0.41
     InputDecoration
    -0.41
    migrationBuilder
    -0.41
    __":
    -0.40
    POSITIVE LOGITS
    9
    0.66
    <bos>
    0.57
    Fordítás
    0.54
     Pfal
    0.52
    ínű
    0.52
    iffion
    0.50
    әрмәләр
    0.50
    nove
    0.50
    AVOR
    0.48
    StateException
    0.48
    Activations Density 0.234%

    No Known Activations