© 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
    2. Joseph Bloom · Initial Gemma-2B SAEs
    3. Gemma-2B
    4. Residual Stream
    5. 0-RES-JB
    6. 412
    Prev
    Next
    INDEX
    Explanations

    mentions of theaters and related events 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.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
    +0.08
    0.3%
    1778
    +0.07
    0.3%
    411
    +0.07
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    520
    +0.08
    0.04
    697
    +0.07
    0.04
    868
    +0.07
    0.03
    Negative Logits
    <bos>
    -1.26
    
    
    -0.71
    ുറ
    -0.66
    /**
    -0.66
    public
    -0.66
    }{||
    -0.65
    <?
    
    -0.65
    //
    -0.64
    const
    -0.63
    /*++
    -0.63
    POSITIVE LOGITS
     affor
    2.03
     increa
    1.97
     theater
    1.96
     theatre
    1.90
     maneu
    1.89
     Theater
    1.85
     aen
    1.84
     Theatre
    1.82
    Theatre
    1.78
     wien
    1.77
    Activations Density 0.098%

    No Known Activations