Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Initial Gemma-2B-IT SAEs
    3. Gemma-2B-IT
    4. Residual Stream
    5. 12-RES-JB
    6. 14723
    Prev
    Next
    INDEX
    Explanations

    technical specifications and statistical data related to hardware performance and advancements

    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
    184
    +0.14
    0.4%
    453
    +0.13
    0.4%
    1150
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    453
    +0.14
    0.05
    184
    +0.13
    0.02
    1311
    +0.09
    0.04
    Negative Logits
     inev
    -1.45
     lele
    -1.43
     wien
    -1.42
     embra
    -1.41
     philanth
    -1.39
     mef
    -1.39
     volunte
    -1.39
     Juf
    -1.39
     emphat
    -1.38
     fta
    -1.37
    POSITIVE LOGITS
     
    0.77
     about
    0.68
     only
    0.65
     less
    0.64
     $
    0.63
     just
    0.62
     around
    0.61
     slightly
    0.61
     more
    0.59
     even
    0.59
    Activations Density 0.250%

    No Known Activations