© 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. 17-GEMMASCOPE-RES-16K
    11. 7656
    Prev
    Next
    INDEX
    Explanations

    phrases that signal time references, such as "in", "since", and "last", indicating temporal context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    MigrationBuilder
    -0.70
    __":
    -0.68
    Demografie
    -0.66
     NUKAT
    -0.63
    ++$
    -0.58
    rrggbb
    -0.54
    preneurship
    -0.54
    XmlType
    -0.53
    TacToe
    -0.53
     protoimpl
    -0.53
    POSITIVE LOGITS
    SequentialGroup
    0.73
     declara
    0.57
     remarks
    0.53
     response
    0.52
    另
    0.52
     kaynağından
    0.52
     reply
    0.50
    hljs
    0.50
     commenting
    0.50
     testifying
    0.50
    Activations Density 0.148%

    No Known Activations