© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 0-RES-JB
    11. 515
    Prev
    Next
    INDEX
    Explanations

    information related to a hotel's amenities and services, travel accommodation details, and technical advisory committee announcements

    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
    783
    +0.08
    0.3%
    966
    +0.08
    0.3%
    1896
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1113
    +0.08
    0.04
    679
    +0.08
    0.04
    824
    +0.07
    0.04
    Negative Logits
    <bos>
    -1.03
    ///**
    -0.67
    HasIndex
    -0.67
    extends
    -0.66
    void
    -0.66
    else
    -0.66
    public
    -0.65
    //{
    -0.65
    /*
    -0.65
    /***
    -0.64
    POSITIVE LOGITS
     weekly
    2.09
     Weekly
    1.89
     Juf
    1.87
     stockholm
    1.85
     monthly
    1.82
    Weekly
    1.76
     affor
    1.76
     increa
    1.72
     maneu
    1.72
     lidl
    1.71
    Activations Density 0.105%

    No Known Activations