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. 1431
    Prev
    Next
    INDEX
    Explanations

    terms related to infrastructure and geography, particularly in an urban context

    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
    674
    +0.20
    0.6%
    184
    +0.17
    0.5%
    764
    +0.15
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    184
    +0.20
    0.01
    764
    +0.17
    0.01
    86
    +0.15
    0.00
    Negative Logits
    Fonto
    -0.69
    tvguidetime
    -0.69
     impon
    -0.66
     Lombar
    -0.64
    Eksteraj
    -0.64
     textil
    -0.63
     Gemeinsame
    -0.61
     Italijani
    -0.61
     geolog
    -0.61
    ἔ
    -0.59
    POSITIVE LOGITS
     shenan
    1.02
     indestru
    0.99
     unwarran
    0.98
     Shakspeare
    0.94
     disagre
    0.94
     apprehen
    0.89
     shewn
    0.87
     quitted
    0.87
     sophistic
    0.86
     encomp
    0.86
    Activations Density 0.027%

    No Known Activations