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. 11230
    Prev
    Next
    INDEX
    Explanations

    complex mathematical notation and symbols

    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
    .
    -0.51
    -
    -0.44
     another
    -0.44
     Another
    -0.44
     جد
    -0.43
    Another
    -0.42
     (
    -0.41
    text
    -0.41
     nakalista
    -0.41
     trang
    -0.41
    POSITIVE LOGITS
     <<<<<<<<<<<<<<
    0.98
    \{\\
    0.82
    writeFieldEnd
    0.80
    ]='\
    0.78
    ]-->
    0.75
    endphp
    0.75
     feltro
    0.75
     Geſ
    0.74
    });*/
    0.74
     Efq
    0.73
    Activations Density 0.504%

    No Known Activations