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. 6261
    Prev
    Next
    INDEX
    Explanations

    names of companies or products related to audio and technology

    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
    32
    +0.18
    1.0%
    370
    +0.14
    0.8%
    1296
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1194
    +0.18
    0.04
    1622
    +0.14
    0.03
    1575
    +0.13
    0.03
    Negative Logits
    <bos>
    -1.91
     guma
    -0.91
     maging
    -0.83
     kahit
    -0.80
     akong
    -0.78
     itong
    -0.77
     maraming
    -0.73
     siyang
    -0.70
     buhay
    -0.69
     hanggang
    -0.69
    POSITIVE LOGITS
     Na
    1.48
     naï
    1.36
     napoli
    1.36
     Châ
    1.32
     Bartholo
    1.31
     casio
    1.29
     accla
    1.27
     madonna
    1.26
    Na
    1.26
     suspic
    1.26
    Activations Density 0.264%

    No Known Activations