© 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. 6856
    Prev
    Next
    INDEX
    Explanations

    phrases related to a specific place or business establishment

    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
    397
    +0.20
    0.9%
    1328
    +0.18
    0.8%
    1065
    +0.14
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    397
    +0.20
    0.03
    370
    +0.18
    0.03
    1328
    +0.14
    0.03
    Negative Logits
     fede
    -0.48
     popolare
    -0.47
    Bec
    -0.47
     Avis
    -0.47
     raste
    -0.47
     revisor
    -0.45
     Hannes
    -0.45
     MTC
    -0.44
    ‎‎
    -0.44
     Bec
    -0.44
    POSITIVE LOGITS
     Str
    1.13
     STR
    1.11
     str
    1.03
    Str
    1.01
     Stra
    1.01
    str
    0.98
    STR
    0.92
    Stra
    0.86
     ftre
    0.81
     strata
    0.79
    Activations Density 0.141%

    No Known Activations