© 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. 7-GEMMASCOPE-RES-16K
    11. 15307
    Prev
    Next
    INDEX
    Explanations

    programming-related terms and structures, particularly those associated with repeated or standard data types in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Busy
    -0.45
    InvalidProtocol
    -0.45
    ########.
    -0.44
    CrossOrigin
    -0.43
    XtraReports
    -0.43
    Soorten
    -0.43
    воль
    -0.42
    udian
    -0.42
    ur
    -0.41
    IVEREF
    -0.41
    POSITIVE LOGITS
    EDEFAULT
    0.88
    IsMutable
    0.76
    omitempty
    0.74
    ]")]
    0.69
    multer
    0.66
    AndEndTag
    0.65
    ControllerTest
    0.64
    glPopMatrix
    0.62
    RetentionPolicy
    0.59
    thenReturn
    0.59
    Activations Density 0.682%

    No Known Activations