© 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. 16-GEMMASCOPE-RES-16K
    11. 4931
    Prev
    Next
    INDEX
    Explanations

    instances of hiding or concealing information

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

    "hide" and its inflections

    np_acts-logits-general · gemini-2.0-flash

    hiding something

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AdapterView
    -0.58
     CWE
    -0.57
    WithFormat
    -0.56
    AllowUser
    -0.53
    WTA
    -0.53
     Sprague
    -0.53
    MigrationBuilder
    -0.53
    ">*</
    -0.52
     formel
    -0.52
    Subject
    -0.51
    POSITIVE LOGITS
     hide
    1.07
     hidden
    1.05
     hiding
    1.05
    MethodManager
    1.04
     Hidden
    1.01
    hiding
    1.00
     hid
    0.98
     Hide
    0.97
     hides
    0.97
    Hiding
    0.95
    Activations Density 0.224%

    No Known Activations