© 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. 4-GEMMASCOPE-RES-16K
    11. 950
    Prev
    Next
    INDEX
    Explanations

    references to journal names and academic citations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     stacks
    -0.52
    chenko
    -0.52
     Pinnacle
    -0.51
    DockStyle
    -0.50
    ADELPHIA
    -0.49
    mehl
    -0.48
    Ārējās
    -0.48
     Cao
    -0.47
    CAUTIONS
    -0.47
    髦
    -0.47
    POSITIVE LOGITS
     JJ
    1.25
    J
    1.20
     J
    1.16
     jc
    1.10
    JJ
    1.09
    j
    1.08
     j
    1.08
     JB
    1.04
    jj
    1.04
     JC
    1.03
    Activations Density 0.722%

    No Known Activations