© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 7164
    Prev
    Next
    INDEX
    Explanations

    transitional phrases and conjunctions that indicate contrasting ideas or conditions

    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
    .
    -0.66
    ↵↵
    -0.57
    ”.
    -0.56
    .”
    -0.54
    WebControls
    -0.54
    ↵
    -0.54
    })$.
    -0.53
    ↵↵↵↵↵
    -0.53
    ]).
    -0.52
    ↵↵↵↵
    -0.51
    POSITIVE LOGITS
    ArgsConstructor
    1.09
    Архівовано
    0.88
     Мексичка
    0.84
    Билгалдахарш
    0.81
     snippetHide
    0.79
    GHIJKLM
    0.78
     tslint
    0.73
     pinulongan
    0.72
    AndEndTag
    0.70
    AxisAlignment
    0.70
    Activations Density 0.531%

    No Known Activations