© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Joseph Bloom · Initial Gemma-2B-IT SAEs
    3. Gemma-2B-IT
    4. Residual Stream
    5. 12-RES-JB
    6. 13297
    Prev
    Next
    INDEX
    Explanations

    text referring to the depiction or description of technological forms

    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
    1343
    +0.12
    0.4%
    699
    +0.09
    0.3%
    11
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    779
    +0.12
    0.02
    1213
    +0.09
    0.02
    270
    +0.08
    0.02
    Negative Logits
     ché
    -0.99
     Chá
    -0.95
     ù
    -0.94
     libere
    -0.91
     parlar
    -0.90
     sopr
    -0.89
     dì
    -0.87
     siff
    -0.87
     ì
    -0.85
     kön
    -0.85
    POSITIVE LOGITS
     unspeak
    0.96
     indescri
    0.84
     shenan
    0.76
     apprehen
    0.76
     horrend
    0.74
     ineffec
    0.69
     overcrow
    0.63
     unimagin
    0.63
     unbear
    0.62
    довлет
    0.61
    Activations Density 0.095%

    No Known Activations