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. 5667
    Prev
    Next
    INDEX
    Explanations

    mentions of events and panel discussions

    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
    +0.24
    0.9%
    1150
    +0.10
    0.4%
    678
    +0.08
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1300
    +0.24
    0.09
    1428
    +0.10
    0.07
    399
    +0.08
    0.08
    Negative Logits
    <bos>
    -2.33
    ⓧ
    -0.75
    ValueGenerated
    -0.69
    /*
    -0.67
     get
    -0.67
    HasAnnotation
    -0.65
    /**
    -0.65
     got
    -0.65
    get
    -0.64
     enter
    -0.64
    POSITIVE LOGITS
     unlaw
    1.93
     maneu
    1.90
     disagre
    1.85
     Minang
    1.80
     sovere
    1.79
     inev
    1.77
     affor
    1.76
     Juf
    1.75
     impractica
    1.75
     reluct
    1.75
    Activations Density 1.799%

    No Known Activations