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. 6-GEMMASCOPE-RES-16K
    6. 5404
    Prev
    Next
    INDEX
    Explanations

    phrases indicating conditions or assumptions based on prior statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.hook_resid_post
    Hook Layer
    6
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     πάνω
    -0.51
    hiza
    -0.50
     sacco
    -0.48
    znik
    -0.46
    endaftaran
    -0.45
     Normandie
    -0.44
    代わりに
    -0.43
    ldb
    -0.42
    Переваги
    -0.42
     act
    -0.42
    POSITIVE LOGITS
     considering
    1.16
    considering
    1.15
    Considering
    1.13
     Considering
    1.13
     mengingat
    1.01
     Given
    0.99
    ostante
    0.96
    Given
    0.95
    given
    0.95
     محفوظة
    0.95
    Activations Density 0.242%

    No Known Activations