© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 28-GEMMASCOPE-RES-16K
    11. 8044
    Prev
    Next
    INDEX
    Explanations

    references to specific organizations or entities within various contexts

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

    "as well" or similar phrases

    np_acts-logits-general · gemini-2.0-flash

    as well as

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     JpaRepository
    -0.43
    tomans
    -0.41
    sibirsk
    -0.40
     Roskov
    -0.39
    ReusableCell
    -0.38
    HomeAsUpEnabled
    -0.36
    BASELINE
    -0.36
    たって
    -0.36
    今度は
    -0.35
    imler
    -0.35
    POSITIVE LOGITS
     plus
    1.88
     along
    1.80
     sowie
    1.61
     serta
    1.53
    along
    1.50
    以及
    1.49
     valamint
    1.48
     además
    1.48
     ainsi
    1.46
     samt
    1.45
    Activations Density 1.527%

    No Known Activations