© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 11008
    Prev
    Next
    INDEX
    Explanations

    names of individuals along with their titles or associations

    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
    1177
    +0.19
    0.7%
    1842
    +0.13
    0.5%
    1577
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    453
    +0.19
    0.16
    2016
    +0.13
    0.14
    1150
    +0.12
    0.03
    Negative Logits
    Lmfao
    -0.96
    Hahah
    -0.92
     pymysql
    -0.87
     exé
    -0.82
     nutella
    -0.79
    Ehh
    -0.79
    Ikr
    -0.78
     recev
    -0.78
    Noice
    -0.74
    Ohhhh
    -0.73
    POSITIVE LOGITS
    setupUi
    0.50
    ---*/
    0.49
    Попис
    0.43
    FormTagHelper
    0.43
    Aholisi
    0.41
     prominently
    0.41
     <=",
    0.41
    Спасылкі
    0.40
     unexpectedly
    0.40
    __':
    0.40
    Activations Density 5.708%

    No Known Activations