© 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. 4198
    Prev
    Next
    INDEX
    Explanations

    instances of comma-separated lists or series in sentences

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

    Text fragments ending in prepositions or conjunctions

    np_acts-logits-general · gemini-2.0-flash

    transfieras,findpost,endphp,Portale

    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
     ๆ
    -0.36
    ๆ
    -0.34
     sentimenti
    -0.32
     ...
    -0.31
     Nuestro
    -0.30
    jątk
    -0.29
     Ott
    -0.29
    matchCondition
    -0.29
     Beine
    -0.28
     many
    -0.28
    POSITIVE LOGITS
     transfieras
    0.83
    verwijspagina
    0.81
    findpost
    0.79
    endphp
    0.78
    Portale
    0.78
    SequentialGroup
    0.75
     AssemblyCulture
    0.75
    IsMutable
    0.75
    __*/
    0.75
     OMITBAD
    0.75
    Activations Density 0.913%

    No Known Activations