Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 8322
    Prev
    Next
    INDEX
    Explanations

    actions related to the concept of taking or receiving

    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
     Chwiliwch
    -0.85
     Paus
    -0.80
    IntoConstraints
    -0.77
    Erreferentziak
    -0.77
    tvguidetime
    -0.76
    PyExc
    -0.72
    CloseOperation
    -0.72
    Portály
    -0.70
    rungsseite
    -0.69
    cfm
    -0.68
    POSITIVE LOGITS
     take
    2.24
     takes
    2.12
    take
    2.00
     Takes
    1.98
    Take
    1.98
    Takes
    1.93
     Take
    1.92
    takes
    1.84
     TAKE
    1.79
    TAKE
    1.60
    Activations Density 0.078%

    No Known Activations