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. 7-GEMMASCOPE-RES-16K
    6. 9524
    Prev
    Next
    INDEX
    Explanations

    string length definitions and related variables

    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
    (©
    -0.85
     Butterfield
    -0.84
    ImagePath
    -0.81
     Bein
    -0.79
    othesis
    -0.75
     Kall
    -0.72
     Hung
    -0.70
     Erb
    -0.69
    teig
    -0.69
     Deak
    -0.68
    POSITIVE LOGITS
     len
    1.55
    len
    1.50
     Len
    1.45
    Len
    1.37
     LEN
    1.25
     Lennox
    1.09
     Lenny
    0.99
    LEN
    0.97
    Lena
    0.94
     lenker
    0.91
    Activations Density 0.028%

    No Known Activations