© 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. 3852
    Prev
    Next
    INDEX
    Explanations

    words related to legal cases and TV series locations

    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
    343
    +0.08
    0.2%
    478
    +0.07
    0.2%
    1121
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1395
    +0.08
    0.04
    343
    +0.07
    0.05
    1415
    +0.07
    0.03
    Negative Logits
     keramik
    -0.91
     makro
    -0.85
     silikon
    -0.83
     kosme
    -0.82
     ananas
    -0.82
     Meksi
    -0.81
     optik
    -0.77
     karton
    -0.75
     antik
    -0.75
     alkoh
    -0.75
    POSITIVE LOGITS
     remain
    1.14
     continue
    1.12
     remained
    1.11
     still
    1.06
    continue
    1.04
     continuing
    1.02
     continued
    1.01
     retain
    1.01
     retained
    1.01
     continues
    1.00
    Activations Density 0.592%

    No Known Activations