© 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. 6365
    Prev
    Next
    INDEX
    Explanations

    instructional content related to diverse topics such as education, trading strategies, journaling, space travel insights, and community feedback

    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
    860
    +0.10
    0.3%
    814
    +0.10
    0.3%
    281
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1919
    +0.10
    0.05
    814
    +0.10
    0.03
    703
    +0.09
    0.04
    Negative Logits
     cioc
    -0.81
     Muito
    -0.81
     swarovski
    -0.81
     Talvez
    -0.76
     carottes
    -0.76
     tille
    -0.75
     répon
    -0.74
     hvil
    -0.74
     Décembre
    -0.73
     Pièces
    -0.73
    POSITIVE LOGITS
    Kilder
    0.52
     pertains
    0.51
     as
    0.51
    Díky
    0.50
     oppose
    0.50
     progresses
    0.49
     As
    0.49
     wished
    0.48
     strive
    0.48
    كما
    0.48
    Activations Density 0.168%

    No Known Activations