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. 15757
    Prev
    Next
    INDEX
    Explanations

    numerical values or percentages related to statistics or data

    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
     AssemblyTitle
    -0.65
    PerformLayout
    -0.64
    DoubleQuotes
    -0.63
    '])->
    -0.60
     GenerationType
    -0.59
     &___
    -0.58
    acchar
    -0.58
    VersionUID
    -0.58
     nadzieję
    -0.57
    ])->
    -0.57
    POSITIVE LOGITS
    URLException
    0.57
    WindowEvent
    0.53
    ValueStyle
    0.53
     SIMBAD
    0.51
    หาร
    0.49
     Clipper
    0.49
     defini
    0.49
    ing
    0.48
     Nore
    0.48
     demag
    0.48
    Activations Density 0.683%

    No Known Activations