© 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. 11858
    Prev
    Next
    INDEX
    Explanations

    file paths and directory structures

    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
    Geografie
    -0.44
     he
    -0.44
     QUESTION
    -0.43
    なこと
    -0.42
     and
    -0.42
     
    -0.41
     far
    -0.41
     form
    -0.41
     as
    -0.41
    ВС
    -0.41
    POSITIVE LOGITS
    ={`/
    0.96
     "..\..\..\
    0.90
    +"/
    0.88
     IBOutlet
    0.82
     ?>/
    0.81
    __(/*!
    0.80
     greateſt
    0.79
     Confucian
    0.78
     './../
    0.78
    DockStyle
    0.78
    Activations Density 0.247%

    No Known Activations