© 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. 18-GEMMASCOPE-RES-16K
    11. 10958
    Prev
    Next
    INDEX
    Explanations

    phrases related to legislative processes and outcomes

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

    Admission/acceptance outcomes (school, military, etc.)

    np_acts-logits-general · gemini-2.0-flash

    granted, allowed, accepted

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SPATH
    -0.72
    ]")]
    -0.65
     Efq
    -0.59
    ")));
    -0.59
     snippetHide
    -0.56
    ".
    -0.56
    .")]
    -0.56
     cherchés
    -0.56
    Abitanti
    -0.55
     Ransom
    -0.54
    POSITIVE LOGITS
     accepted
    1.27
     approved
    1.22
    accepted
    1.07
     approval
    1.06
     successful
    1.05
     acceptance
    1.05
     Approved
    1.02
     APPROVED
    1.01
     Accepted
    1.00
    approved
    0.98
    Activations Density 0.472%

    No Known Activations