© 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. 14450
    Prev
    Next
    INDEX
    Explanations

    names and terms related to political figures and international relations

    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
    871
    +0.14
    0.5%
    1778
    +0.14
    0.5%
    517
    +0.14
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1778
    +0.14
    0.05
    1356
    +0.14
    0.04
    517
    +0.14
    0.03
    Negative Logits
     gesteld
    -0.50
    Referencie
    -0.49
     tež
    -0.48
     najbol
    -0.48
     nė
    -0.47
    æder
    -0.46
     dabar
    -0.46
     pripra
    -0.46
     reikia
    -0.45
     najbolj
    -0.45
    POSITIVE LOGITS
     vertik
    0.75
     völ
    0.75
     VE
    0.72
     vekt
    0.72
     biograf
    0.71
     Vane
    0.71
     Vaugh
    0.70
     alkoh
    0.70
     vx
    0.68
     Vap
    0.68
    Activations Density 0.391%

    No Known Activations