© 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. 4184
    Prev
    Next
    INDEX
    Explanations

    words related to the term "Gra" and its various forms or derivatives, such as references to "Grape" or "Gradle"

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

    starting with "Gra" or "graph"

    np_acts-logits-general · gemini-2.0-flash

    Gra words

    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
    #
    -0.44
     Deta
    -0.42
     Dif
    -0.42
    complexContent
    -0.42
    Kass
    -0.41
     Denn
    -0.41
    /**
    -0.41
    omiast
    -0.40
    */;
    -0.40
    Эзоҳ
    -0.40
    POSITIVE LOGITS
    Gra
    0.63
     Gra
    0.60
     GRA
    0.56
     Normdatei
    0.54
     gra
    0.52
    gra
    0.51
    Гра
    0.45
     GRAV
    0.45
    Grap
    0.44
     grá
    0.44
    Activations Density 0.139%

    No Known Activations