© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 1-GEMMASCOPE-RES-16K
    6. 5894
    Prev
    Next
    INDEX
    Explanations

    references to solitude or being alone

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     anzu
    -0.65
    forName
    -0.65
     незавершена
    -0.64
     Mandi
    -0.63
    jetas
    -0.62
    település
    -0.62
    errHandler
    -0.62
    ypeł
    -0.60
     Versicher
    -0.59
    uthorized
    -0.58
    POSITIVE LOGITS
     alone
    0.96
     Alone
    0.95
     stuck
    0.79
     ALONE
    0.79
    Alone
    0.77
    alone
    0.65
     adhered
    0.64
     merit
    0.64
     âgées
    0.64
     adhering
    0.60
    Activations Density 0.049%

    No Known Activations