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-IT SAEs
    3. Gemma-2B-IT
    4. Residual Stream
    5. 12-RES-JB
    6. 15988
    Prev
    Next
    INDEX
    Explanations

    descriptions related to biological structures or processes, especially those concerning membranes and genetic encoding

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-IT-Residual-Stream-SAEs/gemma_2b_it_blocks.12.hook_resid_post_16384
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    standard
    Context Size
    1,024
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    876
    +0.24
    0.8%
    1842
    +0.13
    0.4%
    752
    +0.11
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    876
    +0.24
    -0.01
    1499
    +0.13
    0.05
    394
    +0.11
    0.04
    Negative Logits
     philanth
    -1.31
     shayari
    -1.27
     shenan
    -1.24
     Incenti
    -1.21
     Krzysz
    -1.18
     pamph
    -1.17
     schoolmaster
    -1.16
     Lmao
    -1.15
     hoody
    -1.15
     bollywood
    -1.11
    POSITIVE LOGITS
     plak
    0.88
     meis
    0.81
     enz
    0.77
     tev
    0.74
     labd
    0.70
     maxime
    0.69
     perle
    0.68
     dien
    0.67
     stik
    0.66
     molecules
    0.66
    Activations Density 0.283%

    No Known Activations