© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 28-GEMMASCOPE-RES-16K
    11. 8257
    Prev
    Next
    INDEX
    Explanations

    negations and contractions in the text

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

    Text before contractions

    np_acts-logits-general · gemini-2.0-flash

    don't, isn't, not

    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
    DockStyle
    -0.45
     chaude
    -0.40
    CppMethod
    -0.39
    SerializeField
    -0.39
    useEffect
    -0.38
     مرئيه
    -0.37
    spire
    -0.36
    hematics
    -0.36
     particulière
    -0.36
    Zacks
    -0.35
    POSITIVE LOGITS
     ProtoMessage
    0.63
     betweenstory
    0.58
    ̈́
    0.53
     Administrativna
    0.53
     мәкалә
    0.53
    TypedDataSet
    0.52
     okuyayım
    0.51
    يكب
    0.51
    GEBURTSDATUM
    0.49
    Rohy
    0.49
    Activations Density 0.111%

    No Known Activations