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. 9511
    Prev
    Next
    INDEX
    Explanations

    mathematical or scientific notation and expressions

    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
     محفوظة
    -0.87
    endphp
    -0.82
     NgModule
    -0.80
    NgModule
    -0.79
    Datuak
    -0.78
     SIMBAD
    -0.76
    nologue
    -0.75
    Jîn
    -0.72
     MonoBehaviour
    -0.72
    iented
    -0.71
    POSITIVE LOGITS
     counter
    0.50
     Counter
    0.47
    …
    0.43
    ",
    0.43
    –
    0.43
     Aditya
    0.42
     lø
    0.42
    igo
    0.42
     also
    0.42
    戊
    0.42
    Activations Density 0.525%

    No Known Activations