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. Joseph Bloom · Initial Gemma-2B-IT SAEs
    3. Gemma-2B-IT
    4. Residual Stream
    5. 12-RES-JB
    6. 13935
    Prev
    Next
    INDEX
    Explanations

    academic affiliations and qualifications

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-IT-Residual-Stream-SAEs/gemma_2b_it_blocks.12.hook_resid_post_16384
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    standard
    Context Size
    1,024
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    1741
    +0.21
    0.7%
    1343
    +0.14
    0.5%
    382
    +0.13
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    16
    +0.21
    0.05
    1343
    +0.14
    0.04
    382
    +0.13
    0.04
    Negative Logits
     €)
    -1.01
     hina
    -1.00
     teras
    -0.98
     kaos
    -0.98
     kask
    -0.96
     antik
    -0.95
     lele
    -0.94
     kamb
    -0.94
     optik
    -0.93
     magis
    -0.92
    POSITIVE LOGITS
     Ph
    0.53
    Etimo
    0.49
     Son
    0.49
     Genesis
    0.48
     maintien
    0.48
     etc
    0.48
     Bir
    0.48
     ,
    0.48
     Ham
    0.48
     Chat
    0.48
    Activations Density 0.179%

    No Known Activations