Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 8098
    Prev
    Next
    INDEX
    Explanations

    mathematical formulas and calculations involving pi

    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
    +0.18
    0.6%
    2015
    +0.16
    0.5%
    1253
    +0.11
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    876
    +0.18
    -0.01
    935
    +0.16
    0.01
    1856
    +0.11
    0.04
    Negative Logits
     biograf
    -0.66
     kriminal
    -0.59
     Akade
    -0.57
     Direktor
    -0.56
     Rektor
    -0.56
     republi
    -0.54
     Jugos
    -0.54
     Demokrat
    -0.54
     Gouver
    -0.53
    styleType
    -0.53
    POSITIVE LOGITS
     alberto
    1.14
     roberto
    1.12
     nicolas
    1.11
     ricardo
    1.10
     sergio
    1.10
     swarovski
    1.09
     rodriguez
    1.08
     fernando
    1.08
     lorenzo
    1.06
     javier
    1.05
    Activations Density 0.256%

    No Known Activations