© 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. 8650
    Prev
    Next
    INDEX
    Explanations

    instances of the verb "to be" and its variations in context

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

    "is" followed by an adjective

    np_acts-logits-general · gemini-2.0-flash

    describing relationships or states

    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
     CreateTagHelper
    -0.57
    BufferException
    -0.50
    ftagPool
    -0.47
     estekak
    -0.46
     Normdatei
    -0.44
    Personendaten
    -0.42
     ویکی‌پدی
    -0.42
     tekem
    -0.41
    providedIn
    -0.39
     skak
    -0.39
    POSITIVE LOGITS
    stateMutability
    0.50
     highly
    0.47
     similar
    0.42
     constrained
    0.42
     subject
    0.42
     intended
    0.40
    consin
    0.40
    )\}$
    0.40
     generally
    0.39
     characterised
    0.39
    Activations Density 1.458%

    No Known Activations