© 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. 28-GEMMASCOPE-RES-16K
    11. 8770
    Prev
    Next
    INDEX
    Explanations

    phrases that refer to conclusions or closures in contexts

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

    "end" or "beginning"

    np_acts-logits-general · gemini-2.0-flash

    beginning or end of things

    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
    NameInMap
    -0.44
    sweise
    -0.41
    Statistiche
    -0.40
    #![
    -0.40
    rouvez
    -0.38
     imb
    -0.37
     Lab
    -0.37
    Hentet
    -0.37
     Parity
    -0.36
     Lattice
    -0.36
    POSITIVE LOGITS
    complexContent
    0.53
    SourceChecksum
    0.51
     المعيارى
    0.49
    disposing
    0.46
    Composable
    0.44
    UrlResolution
    0.44
    httphttps
    0.43
    ReusableCell
    0.42
     voetballer
    0.42
    ChildScrollView
    0.41
    Activations Density 0.157%

    No Known Activations