© 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 SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 0-RES-JB
    11. 1135
    Prev
    Next
    INDEX
    Explanations

    mathematical equations

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-Residual-Stream-SAEs/gemma_2b_blocks.0.hook_resid_post_16384_anthropic
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    torch.float32
    Hook Point
    blocks.0.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    HuggingFaceFW/fineweb
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    241
    +0.09
    0.3%
    920
    +0.09
    0.3%
    849
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    690
    +0.09
    0.05
    1120
    +0.09
    0.04
    184
    +0.09
    0.01
    Negative Logits
     ikiwa
    -0.70
     mwenye
    -0.64
    níci
    -0.60
     utaf
    -0.59
     Février
    -0.59
     wako
    -0.57
     unaweza
    -0.57
     inaweza
    -0.57
     Juillet
    -0.57
     CreateTagHelper
    -0.55
    POSITIVE LOGITS
     avenue
    1.11
     territo
    1.02
     equation
    0.95
     avenues
    0.94
     equations
    0.93
    Avenue
    0.92
     monaster
    0.92
    equations
    0.91
     Equations
    0.87
    Equations
    0.84
    Activations Density 0.327%

    No Known Activations