© 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. 5109
    Prev
    Next
    INDEX
    Explanations

    verbs indicating possession or past experiences

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

    Preceding auxiliary verbs ("has," "have," "had")

    np_acts-logits-general · gemini-2.0-flash

    auxiliary have verbs

    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
     ſche
    -0.41
    AppMethodBeat
    -0.40
     fubject
    -0.36
     gonzález
    -0.35
     ſch
    -0.35
     ſte
    -0.35
     arşivlendi
    -0.35
    ſelf
    -0.34
     cauſe
    -0.34
    linearGradient
    -0.34
    POSITIVE LOGITS
    StoryboardSegue
    0.58
    AndEndTag
    0.57
    addAttribute
    0.55
     got
    0.52
    XmlEnum
    0.52
     plenty
    0.51
     immense
    0.51
    providedIn
    0.50
    eses
    0.50
    Faj
    0.49
    Activations Density 0.237%

    No Known Activations