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. 5-GEMMASCOPE-RES-16K
    6. 13624
    Prev
    Next
    INDEX
    Explanations

    numeric values and their associated parameters in a technical context

    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
     ExecuteAsync
    -0.57
    expandindo
    -0.47
    caccio
    -0.46
    popd
    -0.44
     viewDidLoad
    -0.42
    utiva
    -0.41
     refres
    -0.39
     arkas
    -0.39
     الصد
    -0.38
    허
    -0.37
    POSITIVE LOGITS
    MessageTagHelper
    0.98
    endphp
    0.93
     Chwiliwch
    0.92
    MLLoader
    0.85
    WriteTagHelper
    0.84
    GenerationType
    0.82
    formik
    0.81
    Rhestr
    0.78
    StoreMessageInfo
    0.72
    stdc
    0.70
    Activations Density 3.015%

    No Known Activations