© 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. 18-GEMMASCOPE-RES-16K
    11. 2149
    Prev
    Next
    INDEX
    Explanations

    terms related to locking mechanisms or states

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

    "lock" or "locking"

    np_acts-logits-general · gemini-2.0-flash

    lock and following words

    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
     CreateTagHelper
    -1.14
     betweenstory
    -0.73
     fantasmas
    -0.72
     parlant
    -0.68
    fährt
    -0.65
    ypeł
    -0.65
     varandra
    -0.65
    thâu
    -0.64
    berikut
    -0.64
    quanto
    -0.64
    POSITIVE LOGITS
     Locks
    1.36
     locks
    1.33
    Locks
    1.26
     lock
    1.24
     LOCK
    1.22
     Lock
    1.21
    lock
    1.15
    LOCK
    1.12
    locks
    1.09
     locking
    1.06
    Activations Density 0.117%

    No Known Activations