© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 28-GEMMASCOPE-RES-16K
    11. 2810
    Prev
    Next
    INDEX
    Explanations

    phrases and concepts related to correctness and appropriateness

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

    after "right" or similar correctness/uniqueness terms

    np_acts-logits-general · gemini-2.0-flash

    right, wrong, best, only

    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
     Comunicação
    -0.35
    المشاركات
    -0.33
    الدراسه
    -0.33
     neemt
    -0.32
     memenuhi
    -0.32
     cumplen
    -0.32
     Economía
    -0.32
     Educación
    -0.32
    ￣)
    -0.31
     distrik
    -0.31
    POSITIVE LOGITS
     thing
    0.81
     kind
    0.78
    AndEndTag
    0.77
     kinds
    0.66
     things
    0.63
     amount
    0.62
     sort
    0.61
     AssemblyVersion
    0.60
    HideFlags
    0.60
     coisa
    0.58
    Activations Density 0.251%

    No Known Activations