Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Initial Gemma-2B SAEs
    3. Gemma-2B
    4. Residual Stream
    5. 0-RES-JB
    6. 377
    Prev
    Next
    INDEX
    Explanations

    keywords related to catering services

    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
    369
    +0.07
    0.3%
    214
    +0.06
    0.2%
    228
    +0.06
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    783
    +0.07
    0.04
    1437
    +0.06
    0.05
    732
    +0.06
    0.03
    Negative Logits
    <bos>
    -0.99
    
    
    -0.84
    ⓧ
    -0.83
    }{||
    -0.81
    /**
    -0.80
    <?
    -0.79
     розта
    -0.76
    /*
    -0.73
    ोंने
    -0.72
     близь
    -0.70
    POSITIVE LOGITS
     stockholm
    1.70
     wherea
    1.59
     maneu
    1.58
     wien
    1.58
     bett
    1.57
     Khart
    1.56
     affor
    1.54
     haup
    1.54
     gend
    1.54
     aen
    1.54
    Activations Density 0.510%

    No Known Activations