© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 2-GEMMASCOPE-RES-16K
    6. 7978
    Prev
    Next
    INDEX
    Explanations

    references to forms and formulations in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Hozzáférés
    -0.56
     TestBed
    -0.54
     بتاريخ
    -0.53
    AddTagHelper
    -0.52
    MigrationBuilder
    -0.50
     незавершена
    -0.50
    ="@+
    -0.48
    IntoConstraints
    -0.48
    GTCX
    -0.48
     gonzález
    -0.48
    POSITIVE LOGITS
     form
    3.70
     Form
    3.31
    Form
    3.02
    form
    3.02
     FORM
    2.84
     forms
    2.69
     Forms
    2.36
    FORM
    2.33
     FORMS
    2.14
    forms
    2.11
    Activations Density 0.200%

    No Known Activations