© 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. 7668
    Prev
    Next
    INDEX
    Explanations

    phrases related to complex social or political issues

    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
    1870
    +0.13
    0.4%
    1861
    +0.12
    0.4%
    1265
    +0.08
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1861
    +0.13
    0.06
    143
    +0.12
    0.05
    1503
    +0.08
    0.04
    Negative Logits
     emphat
    -1.70
     accla
    -1.67
     increa
    -1.63
     volunte
    -1.62
     indestru
    -1.57
     impra
    -1.57
     Augu
    -1.54
     disagre
    -1.54
     reluct
    -1.53
     inev
    -1.52
    POSITIVE LOGITS
    <bos>
    1.40
     than
    1.39
    than
    1.08
     hơn
    0.96
     niż
    0.93
    Than
    0.92
     THAN
    0.90
     Than
    0.87
     closer
    0.82
     чем
    0.81
    Activations Density 0.341%

    No Known Activations