© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 12-GEMMASCOPE-RES-16K
    6. 10726
    Prev
    Next
    INDEX
    Explanations

    programming functions and methods related to generating random values

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    oredCriteria
    -0.50
    Opal
    -0.48
    都有
    -0.45
     perde
    -0.44
     LF
    -0.44
    ]<<
    -0.44
     monitore
    -0.44
     MMC
    -0.43
    annis
    -0.43
     Bajo
    -0.42
    POSITIVE LOGITS
    NewGuid
    0.79
    randomUUID
    0.67
     ChromeDriver
    0.66
     propOrder
    0.66
     WaitForSeconds
    0.65
    djangoproject
    0.64
    getExtras
    0.62
    setof
    0.62
     ProtoMessage
    0.61
    siana
    0.60
    Activations Density 0.054%

    No Known Activations