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. 2748
    Prev
    Next
    INDEX
    Explanations

    ISBN numbers

    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
    1978
    +0.11
    0.3%
    453
    +0.10
    0.3%
    490
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    453
    +0.11
    0.05
    1803
    +0.10
    0.04
    1343
    +0.09
    0.05
    Negative Logits
    contentLoaded
    -0.75
    parsedMessage
    -0.71
    Bereits
    -0.69
    Ilustra
    -0.66
     LUMP
    -0.65
    Flere
    -0.65
    Solución
    -0.65
    FOTOS
    -0.64
     Italijani
    -0.63
    Nachdem
    -0.63
    POSITIVE LOGITS
     shenan
    1.18
     emphat
    1.10
     depic
    1.10
     guarante
    1.05
     encomp
    1.05
     attemp
    1.04
     maneu
    1.04
     uninten
    1.03
     disreg
    1.02
     accla
    0.99
    Activations Density 0.204%

    No Known Activations