© 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
    3. Joseph Bloom · Initial Gemma-2B-IT SAEs
    5. Gemma-2B-IT
    7. Residual Stream
    9. 12-RES-JB
    11. 14193
    Prev
    Next
    INDEX
    Explanations

    mentions of specific events or personal interactions

    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
    1978
    +0.22
    0.8%
    674
    +0.22
    0.8%
    599
    +0.17
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    599
    +0.22
    0.07
    468
    +0.22
    0.04
    1224
    +0.17
    0.06
    Negative Logits
    )))));
    -0.60
    archiviato
    -0.53
    انيف
    -0.52
    ))-
    -0.51
    <eos>
    -0.50
    imageio
    -0.48
    GOTREF
    -0.47
    Dichloroethene
    -0.47
     ++)
    -0.47
    ']))
    -0.46
    POSITIVE LOGITS
     Áng
    0.91
     Darío
    0.91
     jorge
    0.90
     javier
    0.90
     alberto
    0.89
     indestru
    0.89
     Abbé
    0.87
     roberto
    0.87
     Rubén
    0.86
     nicolas
    0.85
    Activations Density 1.099%

    No Known Activations