© 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-2-2B
    7. Residual Stream - 16k
    9. 2-GEMMASCOPE-RES-16K
    11. 6899
    Prev
    Next
    INDEX
    Explanations

    references to programming and software versioning

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 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
    <eos>
    -0.47
     achievement
    -0.47
     intent
    -0.47
     Achievement
    -0.45
    intent
    -0.43
    achievement
    -0.42
     Intent
    -0.42
     lost
    -0.41
     σχ
    -0.41
    i
    -0.40
    POSITIVE LOGITS
    ftagPool
    1.02
    Hozzáférés
    0.96
     AssemblyVersion
    0.94
    MigrationBuilder
    0.91
    __":
    0.81
    XmlAccessorType
    0.77
    GraphicsUnit
    0.77
     يتيمه
    0.74
     مشين
    0.73
     calendriers
    0.73
    Activations Density 2.834%

    No Known Activations