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

    Neuronpedia

    APICircuit 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. 6854
    Prev
    Next
    INDEX
    Explanations

    personal stories or biographical information about individuals, possibly related to community involvement

    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
    50
    +0.23
    1.2%
    382
    +0.11
    0.6%
    2034
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    382
    +0.23
    0.09
    2034
    +0.11
    0.09
    1826
    +0.10
    0.04
    Negative Logits
    <bos>
    -3.49
    <?
    -1.26
    ⓧ
    -1.18
    /***
    
    -1.05
     intersper
    -1.00
    
    
    -0.98
    /**
    -0.95
    ///**
    -0.94
     endow
    -0.89
    //*/
    -0.84
    POSITIVE LOGITS
     marea
    0.70
     aparat
    0.63
     maksi
    0.56
     sonda
    0.56
     DialogResult
    0.55
     epoca
    0.54
     alté
    0.54
     alerg
    0.53
     atmosfera
    0.53
     pistolet
    0.53
    Activations Density 0.517%

    No Known Activations