© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 23-GEMMASCOPE-RES-16K
    11. 8683
    Prev
    Next
    INDEX
    Explanations

    code snippets related to input/output operations in JSON processing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    brtc
    -0.56
    DebuggerNonUser
    -0.52
    EndGlobalSection
    -0.51
    PropertyChanged
    -0.48
    ValuePair
    -0.48
     Autorisations
    -0.47
    complexType
    -0.47
    elemField
    -0.46
     GenerationType
    -0.46
    tableFuture
    -0.45
    POSITIVE LOGITS
     stream
    1.35
     Stream
    1.23
    stream
    1.18
     streams
    1.14
    Stream
    1.12
    estream
    1.03
     STREAM
    1.02
     Streams
    1.02
     InputStream
    1.01
     reader
    1.01
    Activations Density 0.455%

    No Known Activations