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-2-2B
    4. Residual Stream - 16k
    5. 2-GEMMASCOPE-RES-16K
    6. 4123
    Prev
    Next
    INDEX
    Explanations

    instances of audience engagement with films or media

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     <<<<<<<<<<<<<<
    -0.61
    ArgsConstructor
    -0.57
    τουργ
    -0.54
     disgrace
    -0.54
    ędzy
    -0.51
    lieu
    -0.51
     biografias
    -0.51
     leçons
    -0.49
    fare
    -0.49
    €¦
    -0.48
    POSITIVE LOGITS
     readers
    0.64
     audiences
    0.59
     propOrder
    0.58
     fans
    0.55
     himo
    0.55
     Readers
    0.53
     FormBuilder
    0.52
     GenerationType
    0.52
     reader
    0.51
     Waray
    0.51
    Activations Density 0.428%

    No Known Activations