© 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. 0-RES-JB
    6. 888
    Prev
    Next
    INDEX
    Explanations

    information related to properties or real estate

    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
    +0.11
    0.5%
    1870
    +0.05
    0.2%
    204
    +0.05
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1802
    +0.11
    0.04
    259
    +0.05
    0.04
    384
    +0.05
    0.03
    Negative Logits
    <bos>
    -1.87
    ⓧ
    -0.92
    ValueGenerated
    -0.86
    <?
    -0.83
    ="#"><
    -0.79
     bring
    -0.78
    public
    -0.78
    /**
    -0.77
    ുറ
    -0.77
    <tfoot>
    -0.77
    POSITIVE LOGITS
     maneu
    2.51
     wien
    2.35
     increa
    2.32
     affor
    2.29
     Juf
    2.27
     stockholm
    2.26
     emphat
    2.23
     impra
    2.23
     Intere
    2.21
     fta
    2.21
    Activations Density 0.135%

    No Known Activations