© 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. 14748
    Prev
    Next
    INDEX
    Explanations

    references to different kinds of fragments and their associated entities, specifically in a coding or technical context

    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
     Efq
    -0.91
     photolibrary
    -0.90
     raiſ
    -0.89
     MCP
    -0.87
     myſelf
    -0.85
     Theſe
    -0.85
     Houſe
    -0.84
     purpoſe
    -0.83
     againſt
    -0.83
     coerci
    -0.82
    POSITIVE LOGITS
     mineral
    0.88
     Mineral
    0.81
    Mineral
    0.70
     MINERAL
    0.68
     Packaging
    0.65
    mineral
    0.65
     Eric
    0.64
     Kraus
    0.62
    Fragment
    0.62
    boxed
    0.62
    Activations Density 0.074%

    No Known Activations