© 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. 1-GEMMASCOPE-RES-16K
    6. 5206
    Prev
    Next
    INDEX
    Explanations

    pronouns, particularly the word "you."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    webElementXpaths
    -0.90
    Geplaatst
    -0.90
    ніципалі
    -0.86
    ьаж
    -0.81
    MigrationBuilder
    -0.81
     nakalista
    -0.80
    awtextra
    -0.79
     Meksiku
    -0.78
     propOrder
    -0.76
     beginnetje
    -0.76
    POSITIVE LOGITS
    Is
    0.47
     preference
    0.46
    mOn
    0.46
    èlement
    0.45
     prawda
    0.45
    @+
    0.42
    cómo
    0.41
    Can
    0.41
    angere
    0.41
    要求
    0.40
    Activations Density 0.210%

    No Known Activations