© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 28-GEMMASCOPE-RES-16K
    6. 9041
    Prev
    Next
    INDEX
    Explanations

    phrases indicating existence or presence

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

    "there is"/"there was" followed by "a" or "no"

    np_acts-logits-general · gemini-2.0-flash

    no / a

    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
     MonoBehaviour
    -0.38
     Serializer
    -0.34
     conscientes
    -0.34
    ReadLine
    -0.34
    onBackPressed
    -0.33
     Jesucristo
    -0.33
     cuir
    -0.32
    clusal
    -0.32
    PopMatrix
    -0.32
    thansa
    -0.32
    POSITIVE LOGITS
     no
    0.79
     plenty
    0.75
     a
    0.67
    considerable
    0.66
     lots
    0.64
    plenty
    0.63
     ample
    0.63
     CanadaChoose
    0.60
     žád
    0.57
     propOrder
    0.57
    Activations Density 0.212%

    No Known Activations