© 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. 890
    Prev
    Next
    INDEX
    Explanations

    multimedia devices and technologies

    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
    50
    +0.09
    0.4%
    555
    +0.06
    0.2%
    1124
    +0.05
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    555
    +0.09
    0.04
    1800
    +0.06
    0.03
    1994
    +0.05
    0.03
    Negative Logits
    <bos>
    -1.47
    /***
    -0.72
    ///////////////
    -0.60
     springfox
    -0.60
    sizeCache
    -0.56
    <?
    -0.55
    новништво
    -0.55
    ोंने
    -0.54
     assemble
    -0.54
     are
    -0.53
    POSITIVE LOGITS
     Traité
    1.53
     affor
    1.42
     Mémoires
    1.28
     Player
    1.28
     Sén
    1.27
     Février
    1.27
     Pièces
    1.27
     Chapitre
    1.22
     player
    1.21
     lidl
    1.21
    Activations Density 0.059%

    No Known Activations