Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 38-GEMMASCOPE-RES-16K
    6. 13200
    Prev
    Next
    INDEX
    Explanations

    backslashes and asterisks in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 38-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_38/width_16k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.38.hook_resid_post
    Hook Layer
    38
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ValueGenerated
    -0.40
     getClass
    -0.36
     isKindOfClass
    -0.32
     doğum
    -0.30
     shoots
    -0.30
     Mo
    -0.29
     REF
    -0.28
     management
    -0.28
     ©️
    -0.28
     sentada
    -0.28
    POSITIVE LOGITS
    ➟
    0.53
    /**
    0.51
     ligiloj
    0.50
    makeatother
    0.50
    évaluateur
    0.50
    XtraEditors
    0.50
     урна
    0.49
     Normdatei
    0.49
     ujednoznacz
    0.48
    ſelben
    0.47
    Activations Density 0.160%

    No Known Activations