© 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. 4591
    Prev
    Next
    INDEX
    Explanations

    phrases related to societal norms and expectations

    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
    +0.12
    0.4%
    674
    +0.12
    0.3%
    1842
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1265
    +0.12
    0.03
    1018
    +0.12
    0.02
    1393
    +0.08
    0.03
    Negative Logits
     lele
    -1.00
     Mú
    -0.78
     kasa
    -0.77
     kac
    -0.76
     gend
    -0.76
     uhr
    -0.75
     puto
    -0.74
     habituellement
    -0.73
     buk
    -0.70
     tuc
    -0.70
    POSITIVE LOGITS
     importantly
    0.74
     perhaps
    0.57
     occasionally
    0.54
     ultimately
    0.53
     sometimes
    0.53
     later
    0.53
     worse
    0.52
     pozdě
    0.52
     worst
    0.51
    devším
    0.51
    Activations Density 0.117%

    No Known Activations