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. 3759
    Prev
    Next
    INDEX
    Explanations

    variables and functions related to software configuration and programming components

    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
     gyakor
    -0.48
     bouch
    -0.48
     getApplication
    -0.48
    ιώ
    -0.47
     (\%)
    -0.47
    seits
    -0.47
    cửa
    -0.47
     echip
    -0.46
    Drei
    -0.46
     colpa
    -0.46
    POSITIVE LOGITS
    ki
    0.88
     صوتيه
    0.80
    #+#
    0.75
     []:
    0.74
    ंदीखरीदारी
    0.71
     <<<<<<<<<<<<<<
    0.71
     ki
    0.70
     AssemblyCulture
    0.69
     MonoBehaviour
    0.69
    ształ
    0.66
    Activations Density 2.522%

    No Known Activations