© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 2-GEMMASCOPE-RES-16K
    11. 4435
    Prev
    Next
    INDEX
    Explanations

    terms related to identification and classification

    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
    Kjelder
    -0.62
     luxe
    -0.53
     htons
    -0.53
    lwjgl
    -0.52
    coaster
    -0.51
    doped
    -0.51
    Descarga
    -0.51
    O
    -0.50
    猩
    -0.50
    尺
    -0.50
    POSITIVE LOGITS
     identification
    2.72
     identify
    2.67
     identifying
    2.65
     identified
    2.65
     identifies
    2.59
     Identify
    2.58
     Identified
    2.58
     identific
    2.48
     Identifying
    2.46
    identify
    2.46
    Activations Density 0.087%

    No Known Activations