© 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
    3. Joseph Bloom · Initial Gemma-2B-IT SAEs
    5. Gemma-2B-IT
    7. Residual Stream
    9. 12-RES-JB
    11. 12810
    Prev
    Next
    INDEX
    Explanations

    mentions of environmental concerns or actions to address them

    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
    919
    +0.10
    0.3%
    1224
    +0.09
    0.3%
    1592
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    919
    +0.10
    0.05
    74
    +0.09
    0.06
    1062
    +0.08
    0.10
    Negative Logits
     accla
    -1.59
     ivi
    -1.55
     nutr
    -1.53
     embra
    -1.52
     casio
    -1.49
     unden
    -1.49
     zimmer
    -1.49
     desir
    -1.47
     dispen
    -1.47
     perfet
    -1.46
    POSITIVE LOGITS
     syndrome
    0.59
    assertEquals
    0.54
    ########.
    0.53
    VYMaps
    0.52
    姆斯
    0.52
    χρι
    0.52
    맞
    0.52
    Према
    0.51
    дых
    0.51
    (__('
    0.50
    Activations Density 1.686%

    No Known Activations