© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Joseph Bloom · Initial Gemma-2B-IT SAEs
    3. Gemma-2B-IT
    4. Residual Stream
    5. 12-RES-JB
    6. 13731
    Prev
    Next
    INDEX
    Explanations

    words related to the processing of information or materials

    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
    1145
    +0.15
    0.5%
    553
    +0.14
    0.5%
    1334
    +0.14
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    789
    +0.15
    0.03
    553
    +0.14
    0.03
    765
    +0.14
    0.02
    Negative Logits
     reele
    -0.51
     Köl
    -0.45
     vinos
    -0.45
     bolj
    -0.43
     cristi
    -0.43
     Uniti
    -0.43
    zeczytaj
    -0.43
     najbolj
    -0.43
     poiché
    -0.42
     gentes
    -0.42
    POSITIVE LOGITS
     processing
    1.17
     Processing
    1.12
     processed
    1.09
     PROCESSING
    1.08
     processors
    1.07
    processing
    1.07
     Processed
    1.05
    Processing
    1.03
     processor
    1.03
    processed
    1.02
    Activations Density 0.049%

    No Known Activations