© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 0-RES-JB
    11. 1544
    Prev
    Next
    INDEX
    Explanations

    descriptions related to structural components like flanges in construction

    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
    1385
    +0.22
    0.7%
    876
    +0.15
    0.5%
    344
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1385
    +0.22
    0.10
    690
    +0.15
    0.07
    876
    +0.09
    0.01
    Negative Logits
     praktik
    -1.50
     hek
    -1.38
     makro
    -1.34
     minimalis
    -1.34
     plak
    -1.31
     elek
    -1.30
     induk
    -1.30
     protokol
    -1.28
     kosme
    -1.27
     alkoh
    -1.27
    POSITIVE LOGITS
     ecru
    1.72
     swarovski
    1.61
     bandeau
    1.55
     pettico
    1.48
     friable
    1.48
     velour
    1.47
     broderie
    1.46
     hairc
    1.45
     hoody
    1.43
     nutella
    1.43
    Activations Density 0.407%

    No Known Activations