© 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. 38-GEMMASCOPE-RES-16K
    6. 15376
    Prev
    Next
    INDEX
    Explanations

    terms related to media and entertainment formats

    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
    LookAnd
    -0.54
     AssemblyCompany
    -0.49
     oprot
    -0.49
     CreateTagHelper
    -0.46
     Administrativna
    -0.45
     kasarigan
    -0.44
    Autoritní
    -0.44
    verwijspagina
    -0.43
    PreExecute
    -0.43
    énario
    -0.42
    POSITIVE LOGITS
     host
    1.45
     hosts
    1.41
     presenters
    1.27
     presenter
    1.23
     hosting
    1.21
     Host
    1.19
     Hosts
    1.19
     segment
    1.16
    host
    1.13
     segments
    1.13
    Activations Density 0.524%

    No Known Activations