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. 341
    Prev
    Next
    INDEX
    Explanations

    information related to geological formations and events, particularly focusing on geological phenomena such as erosion, volcanic rocks, and submarine geology

    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
    906
    +0.15
    0.5%
    1120
    +0.14
    0.5%
    1385
    +0.14
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    736
    +0.15
    0.07
    724
    +0.14
    0.05
    1499
    +0.14
    0.06
    Negative Logits
     klap
    -0.93
     karton
    -0.93
     lapto
    -0.92
     kosme
    -0.87
     Pediat
    -0.86
     stoff
    -0.83
     ideen
    -0.82
     minimalis
    -0.82
     praktik
    -0.80
     keram
    -0.76
    POSITIVE LOGITS
     shewn
    0.82
     ufe
    0.79
     ftu
    0.77
     lefs
    0.77
     laft
    0.75
     fince
    0.75
     fays
    0.74
     oiseau
    0.72
     ftill
    0.72
     ftre
    0.71
    Activations Density 0.469%

    No Known Activations