© 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. 14645
    Prev
    Next
    INDEX
    Explanations

    questions related to understanding and seeking information

    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
     незавершена
    -0.58
     Biôgrafia
    -0.47
    uxxxx
    -0.47
    WithMany
    -0.45
    windowFixed
    -0.44
    <?
    -0.40
    دانشنامهٔ
    -0.40
    ViewFeatures
    -0.40
    bootstrapcdn
    -0.39
     kasarigan
    -0.39
    POSITIVE LOGITS
     do
    2.67
    do
    1.55
     Do
    1.43
    Do
    1.36
     did
    1.28
     DO
    1.16
     до
    0.96
     does
    0.86
     am
    0.75
     are
    0.72
    Activations Density 0.331%

    No Known Activations