© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 38-GEMMASCOPE-RES-16K
    6. 7215
    Prev
    Next
    INDEX
    Explanations

    structured content in scientific or informative writing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 38-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_38/width_16k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.38.hook_resid_post
    Hook Layer
    38
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    出版年
    -0.56
     utafitiHapana
    -0.52
    MessageOf
    -0.42
    úgó
    -0.37
    InputTagHelper
    -0.36
     indisponible
    -0.35
    basicConfig
    -0.35
    ennia
    -0.34
    spyOn
    -0.32
    tifkan
    -0.32
    POSITIVE LOGITS
     ending
    2.92
     Ending
    2.44
     ended
    2.36
     ends
    2.30
     finishing
    2.28
    Ending
    2.28
     endings
    2.27
     finish
    2.22
     concluding
    2.22
     finishes
    2.20
    Activations Density 1.669%

    No Known Activations