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. 7-GEMMASCOPE-RES-16K
    6. 8604
    Prev
    Next
    INDEX
    Explanations

    LaTeX formatting elements used in mathematical equations and expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     المعيارى
    -0.99
     Roskov
    -0.97
    DataAnnotations
    -0.74
    __*/
    -0.74
    enumii
    -0.72
    DockStyle
    -0.70
    InjectMocks
    -0.70
     Bessel
    -0.69
     greateſt
    -0.66
     Normdatei
    -0.66
    POSITIVE LOGITS
    eqnarray
    1.16
    equation
    0.84
    multline
    0.62
     post
    0.57
    مصادر
    0.56
    displaymath
    0.56
    )};
    0.56
    echo
    0.53
     la
    0.52
    
    0.52
    Activations Density 0.448%

    No Known Activations