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. 2-GEMMASCOPE-RES-16K
    6. 3566
    Prev
    Next
    INDEX
    Explanations

    specifications related to dimensions and layouts in a programming or graphical context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 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
    ="#"><
    -0.61
     Zusammen
    -0.55
     ",";
    -0.53
     Kirke
    -0.52
     Ingo
    -0.52
     atom
    -0.51
    chum
    -0.50
     menti
    -0.49
    енча
    -0.49
    ǃ
    -0.49
    POSITIVE LOGITS
    Height
    1.93
    HEIGHT
    1.70
    Width
    1.63
     HEIGHT
    1.34
     Height
    1.31
     Width
    1.20
    WIDTH
    1.13
    SequentialGroup
    1.10
    height
    1.08
    getHeight
    1.08
    Activations Density 0.117%

    No Known Activations