© 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. 7786
    Prev
    Next
    INDEX
    Explanations

    content related to technical instructions or literary content with an emphasis on holistic or meditative practices

    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
    1639
    +0.13
    0.5%
    1271
    +0.13
    0.5%
    298
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1639
    +0.13
    0.03
    1506
    +0.13
    0.03
    1516
    +0.12
    0.03
    Negative Logits
     Palembang
    -0.66
     hej
    -0.65
     kram
    -0.65
     Jambi
    -0.63
     kras
    -0.63
     makro
    -0.63
     naer
    -0.62
     saar
    -0.61
     koch
    -0.59
     meis
    -0.59
    POSITIVE LOGITS
     Mind
    1.18
    Mind
    1.18
     MIND
    1.15
    mind
    1.14
     mind
    1.14
     minds
    1.01
    MIND
    0.98
    minds
    0.90
     Minds
    0.88
    mindedness
    0.75
    Activations Density 0.055%

    No Known Activations