© 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-2-2B
    4. Residual Stream - 16k
    5. 19-GEMMASCOPE-RES-16K
    6. 2526
    Prev
    Next
    INDEX
    Explanations

    instances of quotation marks indicating speech or dialogue

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    writeObject
    -0.51
     wahl
    -0.49
     Redacción
    -0.45
    WriteTagHelper
    -0.45
     coffre
    -0.45
    ती
    -0.44
    ایای
    -0.43
    ее
    -0.42
    ❷
    -0.42
    ofType
    -0.42
    POSITIVE LOGITS
    TagMode
    0.76
    mybatisplus
    0.67
     CreateTagHelper
    0.65
    WebControls
    0.64
    Personensuche
    0.63
    دانشنامهٔ
    0.60
    RTSC
    0.59
     للاسماء
    0.59
    IVEREF
    0.59
    TypedDataSet
    0.59
    Activations Density 0.032%

    No Known Activations