© 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 SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 6-RES-JB
    11. 5911
    Prev
    Next
    INDEX
    Explanations

    phrases related to residential areas or activities

    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
    1178
    +0.14
    0.7%
    1323
    +0.13
    0.7%
    369
    +0.13
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    990
    +0.14
    0.03
    369
    +0.13
    0.03
    1178
    +0.13
    0.03
    Negative Logits
    <bos>
    -1.73
    AutoScale
    -0.60
    MarshalTo
    -0.58
    Κα
    -0.58
     ProtoMessage
    -0.58
    Даль
    -0.58
    hintText
    -0.58
    devise
    -0.56
    o
    -0.55
    englanniksi
    -0.55
    POSITIVE LOGITS
     depic
    1.37
     unden
    1.35
     disagre
    1.35
     Residential
    1.34
     ftu
    1.32
     fuf
    1.30
     maneu
    1.29
    Residential
    1.27
     fta
    1.27
     wien
    1.26
    Activations Density 0.287%

    No Known Activations