© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 25-GEMMASCOPE-RES-16K
    11. 8374
    Prev
    Next
    INDEX
    Explanations

    numerical references and statistical data

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    DoubleQuotes
    -0.69
     doInBackground
    -0.68
    存于互联网档案馆
    -0.64
     ddelweddau
    -0.61
     Ceramby
    -0.57
    audiovisuel
    -0.56
     الحره
    -0.55
    ]")]
    -0.55
    AFX
    -0.55
    RectangleBorder
    -0.53
    POSITIVE LOGITS
     ten
    1.18
     Ten
    1.07
    Ten
    1.05
    ten
    0.93
     TEN
    0.85
     tenth
    0.83
     Tenth
    0.83
    TEN
    0.81
    lO
    0.81
     zehn
    0.78
    Activations Density 0.646%

    No Known Activations