© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 5-GEMMASCOPE-RES-16K
    6. 8813
    Prev
    Next
    INDEX
    Explanations

    pronouns, particularly various forms of "we" and "you."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     autorytatywna
    -1.63
     виправивши
    -1.48
     AssemblyCulture
    -1.41
     disambiguazione
    -1.32
    GEBURTSDATUM
    -1.31
    Hentet
    -1.28
    tvguidetime
    -1.28
    Autoritní
    -1.27
     nakalista
    -1.14
    OGND
    -1.13
    POSITIVE LOGITS
    The
    1.16
    We
    1.01
    In
    0.97
    As
    0.96
    For
    0.93
     The
    0.90
    It
    0.89
    An
    0.86
    On
    0.79
    Do
    0.78
    Activations Density 0.195%

    No Known Activations