© 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. 20-GEMMASCOPE-RES-16K
    6. 15675
    Prev
    Next
    INDEX
    Explanations

    terms and phrases related to cancer research and tumor biology

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

    scientific and research methodology language, particularly related to molecular biology and experimental procedures.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered 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
    TagMode
    -0.44
    ArgsConstructor
    -0.44
     ReactDOM
    -0.43
    andle
    -0.43
    +#+
    -0.43
     DCT
    -0.41
     Ause
    -0.40
     petra
    -0.40
     виправивши
    -0.40
     CSI
    -0.40
    POSITIVE LOGITS
     asociado
    0.45
     wystar
    0.44
    ErrUnexpectedEOF
    0.42
     확인
    0.41
     responded
    0.40
     Überprüfung
    0.40
     asociada
    0.39
    niosek
    0.38
     corresponded
    0.38
     sentito
    0.38
    Activations Density 2.100%

    No Known Activations