© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 28-GEMMASCOPE-RES-16K
    6. 7572
    Prev
    Next
    INDEX
    Explanations

    sentences that contain references to academic or informative writing and their structures

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

    References or descriptions of documents or writings

    np_acts-logits-general · gemini-2.0-flash

    discusses or describes

    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
    seamnă
    -0.41
     carteles
    -0.40
     îna
    -0.38
     unknownFields
    -0.37
     bigli
    -0.37
    diğinde
    -0.36
    lieben
    -0.35
     desbloquear
    -0.35
     Verhält
    -0.34
     preferido
    -0.33
    POSITIVE LOGITS
     discusses
    0.81
     describes
    0.75
     mentions
    0.71
     describe
    0.70
    Descri
    0.70
    discus
    0.67
     mention
    0.66
     StatelessWidget
    0.65
    Discus
    0.65
    descri
    0.62
    Activations Density 0.789%

    No Known Activations