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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 14127
    Prev
    Next
    INDEX
    Explanations

    terms related to systems of transfer and communication in both thermal and information contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Referanser
    -0.47
    RenderAtEndOf
    -0.44
     OnInit
    -0.44
    SOUNDBITE
    -0.43
    enterOuterAlt
    -0.43
    ulosa
    -0.43
     ciudadanía
    -0.43
    ࿐
    -0.42
    ijão
    -0.42
     Савезне
    -0.42
    POSITIVE LOGITS
     transfer
    0.91
     transfers
    0.86
     transfert
    0.80
     Transfers
    0.76
    transfer
    0.75
     Transfer
    0.73
     TRANSFER
    0.72
     transferir
    0.71
     trasferimento
    0.71
    Transfer
    0.71
    Activations Density 1.163%

    No Known Activations