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. 17-GEMMASCOPE-RES-16K
    6. 10743
    Prev
    Next
    INDEX
    Explanations

    possessive pronouns and words related to ownership

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    IUrlHelper
    -0.58
    RetentionPolicy
    -0.52
     Rá
    -0.51
    mainan
    -0.48
    مند
    -0.47
    ionario
    -0.47
     bearers
    -0.47
     estekak
    -0.46
    MnO
    -0.46
    IVATE
    -0.46
    POSITIVE LOGITS
     Mine
    1.10
     MINE
    1.09
     mine
    1.07
     mines
    1.06
    mine
    1.03
    Mine
    1.01
     mining
    0.97
     Ours
    0.96
     Mines
    0.96
    Mines
    0.95
    Activations Density 0.120%

    No Known Activations