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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 1009
    Prev
    Next
    INDEX
    Explanations

    initials or abbreviations that follow a specific format

    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
    +0.15
    0.5%
    1967
    +0.13
    0.4%
    138
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1343
    +0.15
    0.04
    577
    +0.13
    0.03
    928
    +0.10
    0.01
    Negative Logits
    året
    -0.49
     annulus
    -0.49
    leyeb
    -0.48
     vroeger
    -0.48
     Waarom
    -0.46
     verwacht
    -0.46
     unholy
    -0.46
     suchte
    -0.46
     Porém
    -0.46
     Daarnaast
    -0.46
    POSITIVE LOGITS
     krab
    0.97
     plak
    0.92
     meis
    0.91
     robus
    0.91
     Lombar
    0.86
     stik
    0.86
     Ottobre
    0.85
     solidar
    0.84
     obb
    0.84
     glan
    0.82
    Activations Density 0.186%

    No Known Activations