© 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. 30-GEMMASCOPE-RES-16K
    11. 10908
    Prev
    Next
    INDEX
    Explanations

    text that refers to instructions or guidelines

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

    written text or speech

    np_acts-logits-general · gemini-2.0-flash

    what is said or reads

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 30-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_30/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AddTagHelper
    -0.68
    WriteTagHelper
    -0.59
     utafitiHapana
    -0.52
    bootstrapcdn
    -0.51
    RTGC
    -0.47
     وتسجيلات
    -0.45
    ArrowToggle
    -0.44
     يتيمه
    -0.43
    othelioma
    -0.42
    rrggbb
    -0.41
    POSITIVE LOGITS
     says
    1.36
    says
    1.21
    Says
    1.16
     Says
    1.13
     saying
    1.05
     SAYS
    1.04
     zegt
    0.93
     decía
    0.91
     mengatakan
    0.89
     say
    0.85
    Activations Density 0.405%

    No Known Activations