© 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. 211
    Prev
    Next
    INDEX
    Explanations

    information related to dealing with various situations or issues, such as medical conditions, organizational matters, and community disputes

    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
    +0.07
    0.2%
    1919
    +0.07
    0.2%
    687
    +0.06
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1088
    +0.07
    0.03
    34
    +0.07
    0.03
    1622
    +0.06
    0.03
    Negative Logits
    <bos>
    -1.62
    ,
    -0.65
    public
    -0.61
    .
    -0.60
     odkazy
    -0.59
    ret
    -0.58
    didSet
    -0.57
    !
    -0.57
    modb
    -0.57
     become
    -0.57
    POSITIVE LOGITS
     Dealing
    2.17
     dealing
    2.01
    Dealing
    1.92
    dealing
    1.89
     maneu
    1.83
     accla
    1.83
     stockholm
    1.79
     wherea
    1.75
     shenan
    1.75
     affor
    1.74
    Activations Density 0.159%

    No Known Activations