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. 14-GEMMASCOPE-RES-16K
    6. 4168
    Prev
    Next
    INDEX
    Explanations

    buttons and commands related to user interaction in a graphical user interface (GUI)

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ofire
    -0.40
    брь
    -0.38
    paw
    -0.38
    において
    -0.37
     ta
    -0.36
    ніципа
    -0.36
    -
    -0.35
    )}</
    -0.35
    ouns
    -0.34
    top
    -0.34
    POSITIVE LOGITS
    DockStyle
    1.04
    دانشنامهٔ
    0.94
     Chwiliwch
    0.88
    MemoryWarning
    0.85
    GEBURTSDATUM
    0.85
     الدولى
    0.85
    HomeAsUp
    0.83
     мәкал
    0.82
    OGND
    0.80
    contentLoaded
    0.80
    Activations Density 0.110%

    No Known Activations