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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 28-GEMMASCOPE-RES-16K
    6. 2704
    Prev
    Next
    INDEX
    Explanations

    elements indicative of code structure or syntax

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

    Uncommon or unknown words/tokens

    np_acts-logits-general · gemini-2.0-flash

    academic and technical context

    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
     mature
    -0.69
     المعيارى
    -0.67
     maturity
    -0.66
     matured
    -0.64
     matures
    -0.64
     maturing
    -0.59
     Mature
    -0.59
    成熟
    -0.58
    mature
    -0.56
    Mature
    -0.55
    POSITIVE LOGITS
     okuyayım
    0.58
     <=",
    0.54
     estekak
    0.51
     cherchés
    0.49
    })$}
    0.48
     CanadaChoose
    0.46
    )')
    0.45
     Италијани
    0.45
    );?>
    0.45
    }`}
    0.44
    Activations Density 0.103%

    No Known Activations