Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 2-GEMMASCOPE-RES-16K
    6. 2167
    Prev
    Next
    INDEX
    Explanations

    technical programming constructs and syntax, particularly related to device drivers and structures

    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
     itſelf
    -0.87
     Jefus
    -0.81
     Efq
    -0.79
    XmlAccessType
    -0.79
    Попис
    -0.78
     themſelves
    -0.77
     myſelf
    -0.74
     Houſe
    -0.73
     "..\..\..\
    -0.73
    Geplaatst
    -0.73
    POSITIVE LOGITS
    EMPT
    0.52
     const
    0.50
     kap
    0.49
    >());
    0.48
     compor
    0.48
     Ar
    0.46
    endif
    0.44
     le
    0.44
    ¶
    0.44
    +");
    0.43
    Activations Density 0.869%

    No Known Activations