© 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. 7576
    Prev
    Next
    INDEX
    Explanations

    XML or markup-like tags and their associated attributes

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

    Code, names, and technical jargon

    np_acts-logits-general · gemini-2.0-flash

    date, property, or technical identifier

    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
    
    -0.48
     propOrder
    -0.44
    L
    -0.38
    .*")]
    -0.35
    <eos>
    -0.32
     tròn
    -0.32
    周
    -0.32
    Ten
    -0.31
    ten
    -0.31
    2
    -0.30
    POSITIVE LOGITS
     étoient
    0.60
    OOTDTY
    0.59
    minecraftforge
    0.57
    AddressBook
    0.56
     ainfi
    0.55
    parsedMessage
    0.55
     dévelo
    0.54
     plufieurs
    0.54
    InstanceState
    0.52
     gynhyrchwyd
    0.52
    Activations Density 0.049%

    No Known Activations