© 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. 683
    Prev
    Next
    INDEX
    Explanations

    information related to technology products and releases

    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
    +0.10
    0.4%
    1983
    +0.07
    0.3%
    783
    +0.06
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    660
    +0.10
    0.04
    1489
    +0.07
    0.04
    1579
    +0.06
    0.04
    Negative Logits
    <bos>
    -0.90
    ///**
    -0.81
    ⓧ
    -0.78
    public
    -0.78
    BUYER
    -0.76
    ोंने
    -0.76
     continue
    -0.75
     would
    -0.74
    echo
    -0.73
    CreateIndex
    -0.73
    POSITIVE LOGITS
     affor
    2.45
     increa
    2.44
     maneu
    2.44
     impra
    2.31
     inev
    2.30
     stockholm
    2.27
     unden
    2.24
     guarante
    2.23
     effe
    2.23
     fortn
    2.22
    Activations Density 0.122%

    No Known Activations