© 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. 5-GEMMASCOPE-RES-16K
    11. 7758
    Prev
    Next
    INDEX
    Explanations

    repetition of the "@" symbol, indicating annotations or parameters in code documentation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    PerformLayout
    -1.17
    +#+#
    -1.15
    DockStyle
    -1.12
     '\\;'
    -1.09
    Personendaten
    -1.05
    __":
    -1.02
     Paglinawan
    -1.02
    OGND
    -0.99
    دانشنامهٔ
    -0.98
    contentLoaded
    -0.97
    POSITIVE LOGITS
     I
    0.57
    on
    0.54
    li
    0.54
     Do
    0.54
     do
    0.54
    Do
    0.53
     $\
    0.52
     also
    0.52
     G
    0.52
     finally
    0.52
    Activations Density 0.016%

    No Known Activations