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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B-IT SAEs
    5. Gemma-2B-IT
    7. Residual Stream
    9. 12-RES-JB
    11. 14376
    Prev
    Next
    INDEX
    Explanations

    phrases related to announcements or updates

    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
    866
    +0.14
    0.4%
    1334
    +0.10
    0.3%
    1415
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1415
    +0.14
    0.04
    866
    +0.10
    0.04
    1334
    +0.10
    0.03
    Negative Logits
     zove
    -0.85
     teras
    -0.84
     kamb
    -0.82
     makro
    -0.82
     Italij
    -0.81
     matel
    -0.80
     carrefour
    -0.78
     levis
    -0.77
     poff
    -0.76
     fta
    -0.76
    POSITIVE LOGITS
     hear
    0.69
     announce
    0.64
     see
    0.63
     puder
    0.57
     learn
    0.54
     receive
    0.53
     be
    0.53
     finally
    0.52
    Allister
    0.50
    SBATCH
    0.50
    Activations Density 0.118%

    No Known Activations