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. 603
    Prev
    Next
    INDEX
    Explanations

    references to specific geographical locations or directions

    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
    156
    +0.18
    1.0%
    313
    +0.16
    0.9%
    544
    +0.16
    0.9%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1741
    +0.18
    -0.00
    227
    +0.16
    0.07
    1097
    +0.16
    0.06
    Negative Logits
    <bos>
    -0.90
     Sanderson
    -0.57
     mettent
    -0.53
     Pyrr
    -0.52
     Duncan
    -0.52
     Tierney
    -0.51
     Kerr
    -0.50
    hdr
    -0.50
    Ales
    -0.50
    Kir
    -0.49
    POSITIVE LOGITS
     ritard
    0.94
     paff
    0.94
     vna
    0.92
     makro
    0.91
     marseille
    0.90
     ohr
    0.90
     juft
    0.89
     broder
    0.89
     mef
    0.89
     ftre
    0.88
    Activations Density 0.806%

    No Known Activations