© 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-2-9B
    7. Residual Stream - 16k
    9. 0-GEMMASCOPE-RES-16K
    11. 7555
    Prev
    Next
    INDEX
    Explanations

    repeated instances of the word "receive" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_0/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.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    verwijspagina
    -0.50
    InputBorder
    -0.49
    CloseOperation
    -0.47
     متعلقه
    -0.46
     kasarigan
    -0.43
    estacks
    -0.42
     AppCompatTheme
    -0.41
    RUnlock
    -0.39
     utafitiHapana
    -0.39
     cherchez
    -0.39
    POSITIVE LOGITS
     receiving
    3.41
     receive
    3.25
     Receiving
    3.19
     receives
    3.17
     RECE
    3.14
     recie
    3.14
     receipt
    3.08
    Receiving
    3.06
     Receive
    3.06
     received
    3.05
    Activations Density 0.157%

    No Known Activations