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. 5607
    Prev
    Next
    INDEX
    Explanations

    information related to proteomics and data analysis

    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
    +0.26
    1.2%
    1265
    +0.12
    0.5%
    144
    +0.08
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1265
    +0.26
    0.11
    2019
    +0.12
    0.11
    382
    +0.08
    0.09
    Negative Logits
    <bos>
    -3.23
    ⓧ
    -1.11
    <?
    -1.11
    
    
    -1.06
    /**
    -0.94
     intersper
    -0.94
    <?
    
    -0.92
    Transcripción
    -0.84
    Transkript
    -0.83
    /*
    -0.80
    POSITIVE LOGITS
     marea
    0.61
    󠁢
    0.61
     momente
    0.60
     +%
    0.60
    QSize
    0.59
    SBATCH
    0.56
    antastic
    0.55
     geniales
    0.55
    cupertino
    0.55
    stdarg
    0.53
    Activations Density 1.689%

    No Known Activations