© 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. 12463
    Prev
    Next
    INDEX
    Explanations

    terms related to unlocking and extracting files or data

    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
    BASEPATH
    -0.65
    bleib
    -0.51
    NgModule
    -0.51
    httphttps
    -0.51
    InlineData
    -0.49
     utafitiHapana
    -0.47
    LOAT
    -0.46
    avigation
    -0.45
    <tfoot>
    -0.45
    makeText
    -0.45
    POSITIVE LOGITS
     unlocking
    1.16
     unlock
    1.14
     unlocked
    1.04
     unlocks
    1.02
     decrypted
    1.02
     unpack
    1.02
     unravel
    1.00
    ChildScrollView
    1.00
     decrypt
    1.00
    decode
    0.96
    Activations Density 0.324%

    No Known Activations