© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 28-GEMMASCOPE-RES-16K
    11. 6812
    Prev
    Next
    INDEX
    Explanations

    phrases that encourage communication and assistance

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

    following "call", "contact", or "email"

    np_acts-logits-general · gemini-2.0-flash

    contact or email

    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
     OMITBAD
    -0.47
     nargin
    -0.45
    BagConstraints
    -0.40
     bestimm
    -0.40
    Enllaces
    -0.40
     dø
    -0.39
     CanadaChoose
    -0.39
     péri
    -0.39
    JNIEnv
    -0.39
    defn
    -0.39
    POSITIVE LOGITS
     visit
    0.77
     contact
    0.60
     download
    0.59
     visiting
    0.56
     email
    0.56
     visited
    0.55
     contacting
    0.55
    visit
    0.53
     follow
    0.52
     bezoek
    0.51
    Activations Density 0.146%

    No Known Activations