© 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. 8377
    Prev
    Next
    INDEX
    Explanations

    terms that emphasize size or scale

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

    large size

    np_acts-logits-general · gemini-2.0-flash

    words indicating large size

    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
    astify
    -0.54
     <>",
    -0.50
    ApiModelProperty
    -0.45
    routeProvider
    -0.40
    BagConstraints
    -0.40
    matchCondition
    -0.38
    ungsbedingungen
    -0.38
    Alternate
    -0.38
    Gambas
    -0.38
    CompleteListener
    -0.37
    POSITIVE LOGITS
     big
    0.69
     bigger
    0.65
     sized
    0.64
     BIG
    0.63
     gigantic
    0.62
     size
    0.61
     getSize
    0.61
     méret
    0.60
    big
    0.60
     giant
    0.60
    Activations Density 0.321%

    No Known Activations