Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 24-GEMMASCOPE-RES-16K
    6. 14040
    Prev
    Next
    INDEX
    Explanations

    phrases related to functionality and usability in technology

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

    connecting something

    np_acts-logits-general · gemini-2.0-flash

    connecting and plugging

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ⓧ
    -0.78
    VersionUID
    -0.61
    หวัด
    -0.58
    AntiForgeryToken
    -0.58
     utafitiHapana
    -0.56
    ScopeManager
    -0.56
    AutoScaleMode
    -0.55
    tanleria
    -0.55
    cheidet
    -0.54
    IUrlHelper
    -0.54
    POSITIVE LOGITS
     connect
    1.14
     hook
    1.04
     connecting
    1.02
     Connect
    1.00
     connects
    0.99
     hooking
    0.96
    connect
    0.96
     plugging
    0.96
     plug
    0.94
    Connect
    0.94
    Activations Density 0.242%

    No Known Activations