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. 20-GEMMASCOPE-RES-16K
    6. 12242
    Prev
    Next
    INDEX
    Explanations

    programming concepts related to functions and event handling

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Code snippets lacking typical structure

    np_acts-logits-general · gemini-2.0-flash

    constructor and methods

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     CreateTagHelper
    -1.36
    脚注の使い方
    -1.33
     betweenstory
    -1.28
     ProtoMessage
    -1.27
    rungsseite
    -1.26
    principalColumn
    -1.24
     >=",
    -1.20
     otomatig
    -1.20
     Савезне
    -1.18
     ddelweddau
    -1.18
    POSITIVE LOGITS
    <eos>
    0.63
    <unused61>
    0.58
    <unused63>
    0.58
    <unused62>
    0.57
    <unused60>
    0.53
    ↵
    0.51
    ↵↵
    0.51
     R
    0.47
        
    0.47
     O
    0.44
    Activations Density 0.156%

    No Known Activations