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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 5657
    Prev
    Next
    INDEX
    Explanations

    statements regarding the importance of cultural perspectives in understanding conflicts and policy decisions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Text within quotation marks or after quotation marks

    np_acts-logits-general · gemini-2.0-flash

    quotation marks and parentheses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ----
    -1.29
    -----
    -1.20
    ------
    -1.11
     ----
    -1.09
    -------
    -1.06
     .....
    -1.02
    ---
    -1.01
    ----------------
    -0.99
    ---------
    -0.98
     ------
    -0.98
    POSITIVE LOGITS
     «
    3.28
    «
    3.10
    »
    3.05
    ,»
    2.71
    »,
    2.70
     »
    2.68
    .»
    2.66
    ».
    2.63
    ?»
    2.47
     («
    2.43
    Activations Density 0.114%

    No Known Activations