© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 5-GEMMASCOPE-RES-16K
    6. 13702
    Prev
    Next
    INDEX
    Explanations

    conditional statements in programming syntax

    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
     front
    -0.57
     nama
    -0.53
     n
    -0.52
    JAXB
    -0.51
     hoàn
    -0.50
     tình
    -0.49
     Na
    -0.48
     side
    -0.48
     room
    -0.48
     
    -0.48
    POSITIVE LOGITS
    endif
    4.02
     endif
    2.63
    ENDIF
    1.61
    endregion
    1.45
    endfor
    1.40
    endforeach
    1.36
    setVerticalGroup
    1.32
    endpush
    1.22
    ]-->
    1.21
     endforeach
    1.21
    Activations Density 0.036%

    No Known Activations