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. 7-GEMMASCOPE-RES-16K
    6. 2592
    Prev
    Next
    INDEX
    Explanations

    instances of the word "really" and its context, often indicating a degree of emphasis or emotional state

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     iprot
    -0.53
     Trong
    -0.49
     thus
    -0.48
     anledning
    -0.46
     onore
    -0.46
     olympiques
    -0.45
     dropped
    -0.45
     Searle
    -0.44
     Dro
    -0.44
     kerül
    -0.44
    POSITIVE LOGITS
    eabouts
    0.91
     Offisielt
    0.89
     تانيه
    0.79
     bezeichneter
    0.77
    UserScript
    0.77
    ]--;
    0.77
    PerformLayout
    0.75
    ########.
    0.74
    */),
    0.74
    StoreMessageInfo
    0.73
    Activations Density 0.129%

    No Known Activations