© 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-2-9B
    4. Residual Stream - 16k
    5. 14-GEMMASCOPE-RES-16K
    6. 8574
    Prev
    Next
    INDEX
    Explanations

    punctuation and brackets typically used in programming syntax

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_14/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     enfans
    -0.48
     nakalista
    -0.45
     North
    -0.41
    tagHelperRunner
    -0.41
     court
    -0.39
    thebibliography
    -0.39
     ASH
    -0.39
     Polar
    -0.38
     Qing
    -0.38
     Center
    -0.38
    POSITIVE LOGITS
    ())))
    0.59
    _))
    0.59
    ))),
    0.58
    */),
    0.58
    )"),
    0.57
    __)
    0.56
    ).</
    0.56
    )</
    0.55
    ....)
    0.55
    ))).
    0.54
    Activations Density 0.732%

    No Known Activations