© 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
    2. Joseph Bloom · Initial Gemma-2B SAEs
    3. Gemma-2B
    4. Residual Stream
    5. 6-RES-JB
    6. 5998
    Prev
    Next
    INDEX
    Explanations

    information related to restaurant details and descriptions

    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.6.hook_resid_post_16384_anthropic_fast_lr
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    torch.float32
    Hook Point
    blocks.6.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    HuggingFaceFW/fineweb
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    50
    +0.32
    1.3%
    394
    +0.12
    0.5%
    1971
    +0.08
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    394
    +0.32
    0.12
    1937
    +0.12
    0.08
    409
    +0.08
    0.08
    Negative Logits
    <bos>
    -3.17
     prepare
    -0.66
     arrange
    -0.64
     restore
    -0.63
    SourceChecksum
    -0.61
    <?
    -0.59
    displayquote
    -0.58
     activate
    -0.57
     let
    -0.57
    /**
    -0.57
    POSITIVE LOGITS
     affor
    1.52
     swarovski
    1.52
     ecru
    1.50
     tupperware
    1.46
     impra
    1.44
     hairc
    1.43
     peppa
    1.42
     napoli
    1.41
     véhic
    1.41
     milano
    1.41
    Activations Density 2.078%

    No Known Activations