© 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
    3. Joseph Bloom · Initial Gemma-2B-IT SAEs
    5. Gemma-2B-IT
    7. Residual Stream
    9. 12-RES-JB
    11. 14404
    Prev
    Next
    INDEX
    Explanations

    descriptions of historical locations and landmarks

    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
    906
    +0.18
    0.6%
    1120
    +0.18
    0.6%
    872
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    939
    +0.18
    0.08
    906
    +0.18
    -0.01
    1804
    +0.12
    0.06
    Negative Logits
     lapto
    -1.00
     hek
    -0.94
     palet
    -0.93
     krab
    -0.92
     kram
    -0.87
     kado
    -0.86
     gymnas
    -0.85
     psychiat
    -0.84
     nabi
    -0.84
     utop
    -0.82
    POSITIVE LOGITS
     liberality
    0.96
     Gorb
    0.93
     Fg
    0.89
     unlaw
    0.88
     Engraved
    0.87
     McLaugh
    0.85
     Ename
    0.84
     Rine
    0.84
     impractica
    0.84
     McInt
    0.83
    Activations Density 0.773%

    No Known Activations