© 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. 15-GEMMASCOPE-RES-16K
    6. 3779
    Prev
    Next
    INDEX
    Explanations

    numerical values associated with error messages in technical contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/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.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     U
    -0.72
     R
    -0.68
     E
    -0.66
     O
    -0.65
     and
    -0.64
     H
    -0.63
     P
    -0.60
     L
    -0.60
     S
    -0.59
     V
    -0.58
    POSITIVE LOGITS
    +#+#
    1.16
    Personensuche
    1.15
     auroit
    1.07
    )]=
    1.06
    Билгалдахарш
    1.03
    "]=
    1.02
    }`}>
    0.99
    IsContent
    0.98
     purpoſe
    0.97
    Personendaten
    0.95
    Activations Density 0.276%

    No Known Activations