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. 15272
    Prev
    Next
    INDEX
    Explanations

    universities or academic institutions

    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
    227
    +0.16
    0.5%
    1741
    +0.16
    0.5%
    752
    +0.14
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    69
    +0.16
    0.02
    227
    +0.16
    0.03
    203
    +0.14
    0.02
    Negative Logits
     overcrow
    -1.16
     moistened
    -1.05
     intersper
    -1.03
     disreg
    -1.01
     tupperware
    -0.94
     lmfao
    -0.94
     friable
    -0.94
     subgoals
    -0.92
     cushi
    -0.91
     shenan
    -0.89
    POSITIVE LOGITS
     alkoh
    1.69
     kosme
    1.67
     silikon
    1.59
     makro
    1.52
     keramik
    1.51
     antik
    1.48
     kön
    1.46
     akut
    1.45
     kompati
    1.44
     minimalis
    1.44
    Activations Density 0.061%

    No Known Activations