© 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-2-9B
    4. Residual Stream - 16k
    5. 2-GEMMASCOPE-RES-16K
    6. 13268
    Prev
    Next
    INDEX
    Explanations

    punctuation marks and special characters in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 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
     الحره
    -0.79
     miniaturka
    -0.70
     ilustracja
    -0.65
     Normdatei
    -0.62
    ロウィン
    -0.59
    AddTagHelper
    -0.59
     '\\;'
    -0.58
     desmotivaciones
    -0.58
    Espèce
    -0.56
     sukienka
    -0.56
    POSITIVE LOGITS
    formik
    0.44
    支
    0.38
    ="@+
    0.33
    اااا
    0.33
    配
    0.32
    理
    0.32
    اا
    0.32
     US
    0.32
    <0xE3>
    0.32
     upto
    0.31
    Activations Density 0.389%

    No Known Activations