© 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-2-9B
    7. Residual Stream - 16k
    9. 3-GEMMASCOPE-RES-16K
    11. 8178
    Prev
    Next
    INDEX
    Explanations

    numerical and legal references related to detainment and removal processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ↵↵
    -0.39
     a
    -0.31
    -
    -0.27
     bronce
    -0.25
    ↵
    -0.25
     either
    -0.25
     and
    -0.24
     conoc
    -0.24
    );
    -0.23
     ac
    -0.23
    POSITIVE LOGITS
     surla
    0.84
    AddTagHelper
    0.83
     تضيفلها
    0.79
    PerformLayout
    0.78
    ValueStyle
    0.78
     Chwiliwch
    0.77
     Autorizaciones
    0.76
    tagHelperRunner
    0.76
    Портали
    0.75
     صوتيه
    0.73
    Activations Density 0.471%

    No Known Activations