© 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. 2-GEMMASCOPE-RES-16K
    6. 16200
    Prev
    Next
    INDEX
    Explanations

    references to the concept of change or events related to changes in state or value

    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
    htë
    -0.59
    venido
    -0.55
    FormBorderStyle
    -0.51
    beo
    -0.51
    typedef
    -0.50
    $',
    -0.48
    tra
    -0.48
    onsored
    -0.47
    ).—
    -0.47
    ifstream
    -0.47
    POSITIVE LOGITS
     changed
    1.59
     Changed
    1.46
    changed
    1.43
    Changed
    1.38
     amended
    1.13
     improved
    1.11
     altered
    1.11
     revised
    1.11
    improved
    1.09
    CHANGED
    1.07
    Activations Density 0.269%

    No Known Activations