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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Initial Gemma-2B SAEs
    3. Gemma-2B
    4. Residual Stream
    5. 6-RES-JB
    6. 15224
    Prev
    Next
    INDEX
    Explanations

    mentions of municipal activities or entities

    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.6.hook_resid_post_16384_anthropic_fast_lr
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    torch.float32
    Hook Point
    blocks.6.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    HuggingFaceFW/fineweb
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    313
    +0.17
    0.8%
    1392
    +0.11
    0.5%
    1964
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    765
    +0.17
    0.02
    1331
    +0.11
    0.02
    313
    +0.11
    0.02
    Negative Logits
    <bos>
    -1.97
    <?
    -1.13
    ⓧ
    -1.04
     intersper
    -1.02
     disbur
    -0.98
    /**
    -0.93
    
    
    -0.91
     reconno
    -0.88
     trod
    -0.87
     superintend
    -0.86
    POSITIVE LOGITS
     Municipal
    1.24
     municipal
    1.23
    UNICIP
    1.20
    Municipal
    1.13
     munici
    1.11
     Municip
    1.10
     municipality
    1.01
     Munic
    0.98
     Câ
    0.91
     Municipio
    0.88
    Activations Density 0.180%

    No Known Activations