© 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. 3-GEMMASCOPE-RES-16K
    11. 12249
    Prev
    Next
    INDEX
    Explanations

    terms related to legal conferral or granting of rights or statuses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 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
    sbericht
    -0.61
    حوالہ
    -0.61
    setPreferredSize
    -0.59
    gnore
    -0.58
    inco
    -0.56
    prepareStatement
    -0.53
    anging
    -0.51
     ignore
    -0.51
     contention
    -0.50
    ENER
    -0.50
    POSITIVE LOGITS
     bestow
    1.34
     bestowed
    1.17
     besto
    1.14
     conferred
    1.12
     impart
    1.11
     conferring
    1.10
     confer
    1.07
     imparting
    1.07
     imparts
    1.06
     imparted
    1.01
    Activations Density 0.591%

    No Known Activations